CN107703953A - A kind of attitude control method of unmanned plane, device, unmanned plane and storage medium - Google Patents
A kind of attitude control method of unmanned plane, device, unmanned plane and storage medium Download PDFInfo
- Publication number
- CN107703953A CN107703953A CN201710778431.4A CN201710778431A CN107703953A CN 107703953 A CN107703953 A CN 107703953A CN 201710778431 A CN201710778431 A CN 201710778431A CN 107703953 A CN107703953 A CN 107703953A
- Authority
- CN
- China
- Prior art keywords
- unmanned plane
- flight
- time
- information
- flight attitude
- 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
- 238000000034 method Methods 0.000 title claims abstract description 33
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 claims abstract description 16
- 238000009415 formwork Methods 0.000 claims description 45
- 230000036962 time dependent Effects 0.000 claims description 43
- 238000004590 computer program Methods 0.000 claims description 15
- 238000010276 construction Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 2
- 239000004744 fabric Substances 0.000 claims 1
- 235000015170 shellfish Nutrition 0.000 claims 1
- 230000032258 transport Effects 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 3
- 230000008859 change Effects 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 7
- 230000004888 barrier function Effects 0.000 description 6
- 239000013598 vector Substances 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000003044 adaptive effect Effects 0.000 description 4
- 230000007812 deficiency Effects 0.000 description 4
- 238000006116 polymerization reaction Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000000926 separation method Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000009795 derivation Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000686 essence Substances 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000007704 transition Effects 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 or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/08—Control of attitude, i.e. control of roll, pitch, or yaw
- G05D1/0808—Control of attitude, i.e. control of roll, pitch, or yaw specially adapted for aircraft
- G05D1/0816—Control of attitude, i.e. control of roll, pitch, or yaw specially adapted for aircraft to ensure stability
- G05D1/0825—Control of attitude, i.e. control of roll, pitch, or yaw specially adapted for aircraft to ensure stability using mathematical models
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/04—Traffic conditions
-
- 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
- G05D1/08—Control of attitude, i.e. control of roll, pitch, or yaw
- G05D1/0808—Control of attitude, i.e. control of roll, pitch, or yaw specially adapted for aircraft
Abstract
The applicable field of computer technology of the present invention, there is provided a kind of attitude control method of unmanned plane, device, unmanned plane and storage medium, this method include:The flight information at unmanned plane current time is gathered by the sensor on unmanned plane, the flight information is arranged to the observation data of variable structure discrete dynamic bayesian networks, the flight attitude information of unmanned plane subsequent time is generated by variable structure discrete dynamic bayesian networks, the flight attitude information is sent to the earth station associated with unmanned plane, flight attitude information is translated as into flight attitude by earth station to instruct, and the flight attitude instruction that satellite receiver returns, according to default there is time-varying sliding mode controller and flight attitude to instruct, flight to unmanned plane is controlled, so as to be effectively improved complicated dynamic scene (such as, disaster relief scene) under UAV Flight Control robustness and precision, it is effectively improved the stability of unmanned plane during flying.
Description
Technical field
The invention belongs to UAV Attitude control technology field, more particularly to a kind of attitude control method of unmanned plane, dress
Put, unmanned plane and storage medium.
Background technology
In the living environment of people, natural calamity and man-made disaster are happened occasionally, and live disaster affected people after calamity is carried out
Success detects and rescue, turns into the important topic that researcher need to face.Compared to other Disaster Relief Robots, SUAV by
Site environment influences the advantages that small, action is rapid, implementation rate is high and the optional span of volume is big so that large quantities of scientific research personnel
The application of unmanned plane in this respect is developed incessantly.
Multi-level unknown magnitude, the noise jamming of unknown frequency for airborne aircraft be present, such as:Space office
Portion it is uncertain air-dry disturb, air pressure rises and falls and temperature change, upper and lower during body itself rotor wing rotation flutters and body itself
Parameter Perturbation, the motive torque in the uncertain source in the external world.These disturb the stability for causing UAV Attitude to turn into unmanned plane
Whether people search's action is able to the matter of utmost importance carried out.
At present, there is the method that researcher proposes the four rotor wing unmanned aerial vehicle attitude datas fusion based on Kalman filter,
This method reduces the amount of calculation that unmanned plane flies control processor to a certain extent, but can not under the scene of environment dynamic change
Real time data is obtained, reduces the antijamming capability of unmanned plane.In addition, there is researcher to propose to pass through in extended mode tracker
The observation of Position disturbance carries out disturbance compensation to initial control output quantity, but during transition is arranged, Nonlinear Tracking Differentiator
Interest for delinquency be present to the differential signal of controlled device extraction, be unfavorable for follow-up disturbance compensation.In addition, according to Euler-glug
Bright day kinetic model, utilize the flight control method of radial direction base (RBF) neural fusion unmanned plane, it is not necessary to Euler-drawing
The prior information of Ge Lang kinetic models, and good path tracking effect is obtained, but nerve is trained in this method
The resource consumption of network is larger, and neutral net is very high to the precise requirements of Euler-Lagrange kinetic model.Pass through base
In the method that the robust controller of Nonlinear Disturbance Observer carries out flight control to unmanned plane, four rotor wing unmanned aerial vehicles essence is realized
The higher Trajectory Tracking Control of degree, but this observer needs accurate mathematical modeling, its robustness is not strong, when unmanned plane is deposited
In uncertain and interference, observer performance can reduce.Cutting in sliding formwork control is adaptively adjusted using fuzzy neural network
The method for changing gain, there is larger lifting in control accuracy and Lu Bang tracing controls, but because fuzzy neural network is subordinate to
Easily there is relatively large deviation in the design of threshold function table, poor to the adaptive ability of environment, finally influence control effect.
The content of the invention
It is an object of the invention to provide a kind of attitude control method of unmanned plane, device, unmanned plane and storage medium, purport
In the case of unmanned plane is by interference such as uncertain wind, air pressure fluctuating and temperature changes in actual environment of the solution in complexity,
The problem of antijamming capability of unmanned plane is insufficient in the prior art, UAV Flight Control robustness is not strong, precision deficiency.
On the one hand, the invention provides a kind of attitude control method of unmanned plane, methods described to comprise the steps:
By default sensor on unmanned plane, the flight information at the unmanned plane current time is gathered;
The flight information is arranged to the observation data of default Bayesian network, the nothing is generated by Bayesian network
The flight attitude information of man-machine subsequent time, the Bayesian network combine default expertise distributed model and train to obtain
Variable structure discrete dynamic bayesian networks;
The flight attitude information is sent to the earth station associated with the unmanned plane, by the earth station by described in
Flight attitude information is translated as flight attitude instruction, and receives the flight attitude instruction that the earth station returns;
Instructed according to the default sliding mode controller with Time-dependent sliding surface and the flight attitude, to the unmanned plane
Flight is controlled.
On the other hand, the invention provides a kind of attitude-control device of unmanned plane, described device to include:
Information acquisition unit, for by default sensor on unmanned plane, gathering flying for the unmanned plane current time
Row information;
Posture generation unit, for the flight information to be arranged to the observation data of default Bayesian network, pass through institute
The flight attitude that Bayesian network generates the unmanned plane subsequent time is stated, the Bayesian network is to combine default expertise
Distributed model trains obtained variable structure discrete dynamic bayesian networks;
Instruction sending unit, for the flight attitude to be sent into the earth station associated with the unmanned plane, pass through institute
State earth station and the flight attitude information is translated as flight attitude instruction, and receive the flight appearance that the earth station returns
State instructs;And
Flight control units, for being referred to according to the default sliding mode controller with Time-dependent sliding surface and the flight attitude
Order, the flight to the unmanned plane are controlled.
On the other hand, present invention also offers a kind of unmanned plane, including memory, processor and it is stored in the storage
In device and the computer program that can run on the processor, realized as above during computer program described in the computing device
State the step described in a kind of attitude control method of unmanned plane.
On the other hand, present invention also offers a kind of computer-readable recording medium, the computer-readable recording medium
Computer program is stored with, a kind of gesture stability side of unmanned plane as described above is realized when the computer program is executed by processor
Step described in method.
The present invention gathers the flight information at unmanned plane current time by the sensor on unmanned plane, and the flight information is set
The observation data of Bayesian network are set to, the flight attitude information of unmanned plane subsequent time are generated by Bayesian network, by this
Flight attitude information is sent to the earth station associated with unmanned plane, and flight attitude information is translated as into flight attitude by earth station
Instruction, and the flight attitude instruction that satellite receiver returns, according to the default sliding mode controller with Time-dependent sliding surface and fly
Row attitude command, the flight to unmanned plane are controlled, so as to the structure changes dynamic discrete Bayes by combining expertise
Network, state of flight of the unmanned plane under complex dynamic environment is made inferences, passes through the sliding formwork control with Time-dependent sliding surface
Device is effectively tracked to the flight path of unmanned plane, is effectively improved the robustness and precision of UAV Flight Control,
So that the stability of unmanned plane flight in complex dynamic environment (such as disaster relief environment) is stronger.
Brief description of the drawings
Fig. 1 is a kind of implementation process figure of the attitude control method for unmanned plane that the embodiment of the present invention one provides;
Fig. 2 is a kind of structural representation of the attitude-control device for unmanned plane that the embodiment of the present invention two provides;
Fig. 3 is a kind of structural representation of the attitude-control device for unmanned plane that the embodiment of the present invention three provides;And
Fig. 4 is the structural representation for the unmanned plane that the embodiment of the present invention four provides.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
It is described in detail below in conjunction with specific implementation of the specific embodiment to the present invention:
Embodiment one:
Fig. 1 shows the implementation process of the attitude control method for the unmanned plane that the embodiment of the present invention one provides, for the ease of
Illustrate, illustrate only the part related to the embodiment of the present invention, details are as follows:
In step S101, pass through default sensor on unmanned plane, the flight information at collection unmanned plane current time.
Unmanned plane during flying gesture stability of the present invention suitable for complex dynamic environment (such as disaster relief environment).Nothing can be passed through
Man-machine default monocular visible light sensor (or more mesh visible light sensors), infrared light transducer[sensor, RGBD sensors, swash
Optar, barometer and alignment system etc., gather the flight information at unmanned plane current time, and flight information may include nothing
Man-machine visual information, position, height and flight attitude etc., nobody is controlled according to the flight information collected so as to follow-up
Machine avoiding obstacles fly.
In step s 102, flight information is arranged to the observation data of default Bayesian network, passes through Bayesian network
The flight attitude information of unmanned plane subsequent time is generated, Bayesian network is to combine default expertise distributed model to train to obtain
Variable structure discrete dynamic bayesian networks.
In embodiments of the present invention, Bayesian network is to combine the change knot that default expertise distributed model trains to obtain
Structure discrete dynamic Bayesian network.Flight information can be arranged to the observation data of structure changes dynamic bayesian network, pass through change
Adaptive reasoning algorithm in structural separation dynamic bayesian network, the flight attitude information of unmanned plane subsequent time is generated, with
Unmanned plane is set to avoid the barrier in environment.
In embodiments of the present invention, the network structure of variable structure discrete dynamic bayesian networks can be divided into three layers:Bottom is
Observer nodes, the evidence of observer nodes are the flight information that sensor collects;The second layer is concealed nodes, and concealed nodes are nothing
Man-machine environmental situation assesses node, for assessing interference type, interference strength and the unmanned plane in unmanned plane local environment
With the relative distance of barrier etc.;Top layer is decision node, i.e., carries out decision-making to the flight attitude information of unmanned plane subsequent time,
For example, before interference in the environment occurs, decision node includes two class states, that is, passes through or hide, interference in the environment goes out
After now, decision node includes three class states, that is, advance-hide, stop-hiding, retreat-hide, with according in concealed nodes
Varying environment assess and different modes are carried out to the interference in environment hidden.Variable structure discrete dynamic bayesian networks finally push away
Manage the flight attitude information of the state, i.e. unmanned plane subsequent time of obtained decision node.
Preferably, the structure of expertise distributed model and Bayesian network can be realized by following step:
(1) sample data of unmanned plane during flying is gathered by the sensor on unmanned plane, and builds expertise distributed mode
Type and Bayesian network.
(2) according to the evidence of concealed nodes in sample data, expertise distributed model and Bayesian network, to Bayes
The parameter of network optimizes, and generates the Bayesian network trained.
In embodiments of the present invention, variable structure discrete dynamic bayesian networks reasoning is sharp i.e. under the network structure built
With the evidence of network model parameter and observer nodes go calculate concealed nodes, decision node value probability, according to probability
It can determine that the value of concealed nodes, decision node.Due in the flight environment of vehicle of complexity, disturbing time and the space tool of appearance
There is a uncertainty, variable structure discrete dynamic bayesian networks need under a small amount of observation data (namely unmanned plane in the short time
Under the sample data that upper sensor collects) make a response, it is likely that produce the incomplete phenomenon of sample data.Therefore, can lead to
Cross and establish corresponding expertise distributed model, the sampled data of expertise distributed model is incorporated into structure changes Discrete Dynamic
In the parameter learning of Bayesian network, so as to be effectively reduced to a certain extent parameter learning process to big-sample data according to
Rely so that the variable structure discrete dynamic bayesian networks after parameter learning obtain accurate reasoning knot under Small Sample Database
Fruit.Wherein, expertise can be obtained by building Di Li Crays (Dirichlet) distributed model or beta (Beta) distributed model
Distributed model.
In embodiments of the present invention, in variable structure discrete dynamic bayesian networks, can according to the evidences of observer nodes (or
Value) forward inference obtains the evidence of concealed nodes.According to the sample number that sensor collects on the evidence of concealed nodes, unmanned plane
According to this and expertise distributed model collection sample, the parameter of variable structure discrete dynamic bayesian networks can be optimized,
The variable structure discrete dynamic bayesian networks trained.
In step s 103, flight attitude information is sent to the earth station associated with unmanned plane, will be flown by earth station
Row attitude information is translated as flight attitude instruction, and the flight attitude instruction that satellite receiver returns.
In embodiments of the present invention, the flight attitude information that will be obtained by variable structure discrete dynamic bayesian networks reasoning
The earth station associated with unmanned plane is sent to, earth station's flight attitude according to corresponding to generating the flight attitude information instructs, and
Flight attitude instruction is returned into unmanned plane, so that unmanned plane is according to the tune of the flight attitude of return instruction progress flight attitude
It is whole.
In step S104, instructed according to the default sliding mode controller with Time-dependent sliding surface and flight attitude, to nothing
Man-machine flight is controlled.
In embodiments of the present invention, the sliding mode controller with Time-dependent sliding surface is pre-designed, to pass through the sliding formwork control
To nothing when device is to solve the problems, such as that traditional sliding formwork control reaches stage robustness deficiency, while eliminate the selection of sliding mode controller parameter
Man-machine upper bound is known to be required.The sliding mode controller with Time-dependent sliding surface can be designed beforehand through following step:
(1) the initial tracking error of default UAS model is built, time-varying sliding formwork is built according to initial tracking error
Face.
(2) time-varying sliding formwork control ratio is built according to the Time-dependent sliding surface of structure, so that the track of UAS model is protected
Hold on Time-dependent sliding surface.
In embodiments of the present invention, UAS mathematical modeling is represented by:
Wherein, ξ=[x y z]T∈R3For the center of gravity of unmanned plane under inertial coodinate system
Position, V=[vx vy vz]T∈R3For the linear velocity of unmanned plane under inertial coodinate system, m is unmanned plane quality, η=[φ θ ψ]T
For the attitude vectors of unmanned plane under inertial coodinate system, φ, θ and ψ are respectively roll angle, the angle of pitch and yaw angle, Ω=[p q r
]TFor the angular speed under unmanned plane body axis system, p, q, r are respectively angular velocity in roll, rate of pitch and yaw rate, J
∈R3×3For the moment of inertia matrix under unmanned plane body axis system, H is that the attitude vectors under unmanned plane body axis system change square
Battle array, FLFor the total life of four rotors of unmanned plane, FDFor the drag overall of four rotors of unmanned plane, ΓfThe lift being subject to for unmanned plane
Torque, ΓaThe Pneumatic friction torque being subject to for unmanned plane.
In embodiments of the present invention, the gesture stability target of unmanned plane is:In the case where unmanned plane perturbating upper bound is unknown,
Robust Control Law is designed, with by controlling fuselage deflection angle δ=[δφ,δθ,δψ]TRealize the attitude angle in being instructed to flight attitudeIt is tracked, that is, has:
Set up, wherein,For system tracking error, δφ、δθ、δψ
The respectively deflection angle of roll angle, the angle of pitch and yaw angle, φc、θcWithThe rolling of attitude angle respectively in flight attitude instruction
Angle, the angle of pitch and yaw angle.
In embodiments of the present invention, can be in traditional sliding formwork in order to eliminate the arrival section of traditional sliding formwork, ensure global robustness
On the basis of face, add an exponential term related to the initial tracking error of system so that UAS model from it is initial when
Quarter is on sliding-mode surface.Obtained Time-dependent sliding surface is built to be represented by:
Wherein, Ae-atFor the exponential term related to the initial tracking error of system, a ∈ R+Determine
Time-dependent sliding surface to when not variable sliding-surface velocity of approach, A ∈ R3For the parameter matrix related to unmanned plane original state, use
To ensure S (0)=03×1, can be calculatedΛ is parameter preset.According to what is built
Time-dependent sliding surface structure time-varying sliding formwork control ratio (i.e. Robust Control Law):
Wherein, η=diag { η1,η2,η3It is handoff gain matrix,
And meet ηj> Δs υjmax, Δ υjmaxFor Δ υjMaximum, whenWhen,WhenWhen, sat (sj(t))=sgn (sj (t)),For the boundary layer thickness of Time-dependent sliding surface, j=1,2,3.
(3) sliding mode controller is built according to time-varying sliding formwork control ratio, and builds sliding mode observer, sliding mode observer is used for pair
The calculating of time-varying sliding formwork control ratio carries out noise processed.
In embodiments of the present invention, sliding mode controller is built according to time-varying sliding formwork control ratio, sliding mode controller is represented by:
Wherein, z1=δ is attitude angle vector.
In embodiments of the present invention, sliding mode observer is built according to time-varying sliding formwork control ratio, sliding mode observer is represented by:
Wherein, r1、r2、r3For observer parameter and r1,r2,r3∈R+,Respectively z1And z2Observation,For polymerization disturbance Δ υ estimate.By the expression formula of time-varying sliding formwork control ratio
Understand, when designing time-varying sliding formwork control ratio, it is necessary to use UAV Attitude angular derivative information, and because attitude angle is made an uproar
The influence of sound, high-frequency noise can be introduced by directly carrying out derivation to attitude angle, so as to be obtained by constructing high_order sliding mode control device
Required attitude angle derivative information, and the polymerization disturbance to time-varying sliding formwork control ratio is estimated, so as to effectively improve nobody
The precision of machine flight attitude control.
In embodiments of the present invention, after the flight information at unmanned plane current time is collected, Bayesian network pair is passed through
The flight information is handled, and generates the flight attitude information of unmanned plane subsequent time, will by the earth station associated with unmanned plane
The flight attitude information is translated as flight attitude instruction, according to the default sliding mode controller with Time-dependent sliding surface and the flight
Attitude command, the flight to unmanned plane are controlled, so as to the structure changes dynamic discrete Bayesian network by combining expertise
Network, state of flight of the unmanned plane under complex dynamic environment is made inferences, pass through the sliding formwork control mould with Time-dependent sliding surface
Type is effectively tracked to the flight path of unmanned plane, is effectively improved the robustness and precision of UAV Flight Control,
So that the stability that unmanned plane flies in complex dynamic environment is stronger.
Embodiment two:
Fig. 2 shows a kind of structure of the attitude-control device for unmanned plane that the embodiment of the present invention two provides, for the ease of
Illustrate, illustrate only the part related to the embodiment of the present invention, including:
Information acquisition unit 21, for by default sensor on unmanned plane, gathering the flight at unmanned plane current time
Information.
In embodiments of the present invention, (or the more mesh visible rays of default monocular visible light sensor on unmanned plane can be passed through
Sensor), infrared light transducer[sensor, RGBD sensors, laser range finder, barometer and alignment system etc., collection unmanned plane is worked as
The flight information at preceding moment, flight information may include visual information, position, height and flight attitude of unmanned plane etc., so as to
It is follow-up to be flown according to the flight information collected control unmanned plane avoiding obstacles.
Posture generation unit 22, for flight information to be arranged to the observation data of default Bayesian network, pass through pattra leaves
This network generates the flight attitude information of unmanned plane subsequent time, and Bayesian network is to combine default expertise distributed model instruction
The variable structure discrete dynamic bayesian networks got.
In embodiments of the present invention, Bayesian network is to combine the change that default expertise distributed model trains to obtain
Structural separation dynamic bayesian network.Flight information can be arranged to the observation data of variable structure discrete dynamic bayesian networks,
Pass through the adaptive reasoning algorithm in variable structure discrete dynamic bayesian networks, the flight attitude letter of generation unmanned plane subsequent time
Breath, so that unmanned plane avoids the barrier in environment.
In embodiments of the present invention, the network structure of variable structure discrete dynamic bayesian networks can be divided into three layers:Bottom is
Observer nodes, the evidence of observer nodes are the flight information that sensor collects;The second layer is concealed nodes, and concealed nodes are nothing
Man-machine environmental situation assesses node, for assessing interference type, interference strength and the unmanned plane in unmanned plane local environment
With the relative distance of barrier etc.;Top layer is decision node, i.e., carries out decision-making to the flight attitude information of unmanned plane subsequent time,
For example, before interference in the environment occurs, decision node includes two class states, that is, passes through or hide, interference in the environment goes out
After now, decision node includes three class states, that is, advance-hide, stop-hiding, retreat-hide, with according in concealed nodes
Varying environment assess and different modes are carried out to the interference in environment hidden.Variable structure discrete dynamic bayesian networks finally push away
Manage the flight attitude information of the state, i.e. unmanned plane subsequent time of obtained decision node.
Instruction sending unit 23, for flight attitude information to be sent into the earth station associated with unmanned plane, pass through ground
Stand and flight attitude information is translated as flight attitude instruction, and the flight attitude instruction that satellite receiver returns.
In embodiments of the present invention, the flight attitude information that will be obtained by variable structure discrete dynamic bayesian networks reasoning
The earth station associated with unmanned plane is sent to, earth station's flight attitude according to corresponding to generating the flight attitude information instructs, and
Flight attitude instruction is returned into unmanned plane, so that unmanned plane is according to the tune of the flight attitude of return instruction progress flight attitude
It is whole.
Flight control units 24, instructed for the default sliding mode controller with Time-dependent sliding surface and flight attitude, it is right
The flight of unmanned plane is controlled.
In embodiments of the present invention, the sliding mode controller with Time-dependent sliding surface is pre-designed, to pass through the sliding formwork control
To nothing when device is to solve the problems, such as that traditional sliding formwork control reaches stage robustness deficiency, while eliminate the selection of sliding mode controller parameter
Man-machine upper bound is known to be required.Flight attitude instruction is carried out by the sliding mode controller with Time-dependent sliding surface
Reason, realize the flight control to unmanned plane.
In embodiments of the present invention, after the flight information at unmanned plane current time is collected, Bayesian network pair is passed through
The flight information is handled, and generates the flight attitude information of unmanned plane subsequent time, will by the earth station associated with unmanned plane
The flight attitude information is translated as flight attitude instruction, according to the default sliding mode controller with Time-dependent sliding surface and the flight
Attitude command, the flight to unmanned plane are controlled, so as to the structure changes dynamic discrete Bayesian network by combining expertise
Network, state of flight of the unmanned plane under complex dynamic environment is made inferences, pass through the sliding formwork control mould with Time-dependent sliding surface
Type is effectively tracked to the flight path of unmanned plane, is effectively improved the robustness and precision of UAV Flight Control,
So that the stability that unmanned plane flies in complex dynamic environment is stronger.
Embodiment three:
Fig. 3 shows the structure of the attitude-control device for the unmanned plane that the embodiment of the present invention three provides, for convenience of description,
The part related to the embodiment of the present invention is illustrate only, including:
Network model construction unit 31, for gathering the sample data of unmanned plane during flying by the sensor on unmanned plane,
And build expertise distributed model and Bayesian network.
Network training unit 32, for according to hiding section in sample data, expertise distributed model and Bayesian network
The evidence of point, optimizes to the parameter of Bayesian network, generates the Bayesian network trained.
In embodiments of the present invention, variable structure discrete dynamic bayesian networks reasoning is sharp i.e. under the network structure built
With the evidence of network model parameter and observer nodes go calculate concealed nodes, decision node value probability, according to probability
It can determine that the value of concealed nodes, decision node.Due in the flight environment of vehicle of complexity, disturbing time and the space tool of appearance
There is a uncertainty, variable structure discrete dynamic bayesian networks need under a small amount of observation data (namely unmanned plane in the short time
Under the sample data that upper sensor collects) make a response, it is likely that produce the incomplete phenomenon of sample data.Therefore, can lead to
Cross and establish corresponding expertise distributed model, the sampled data of expertise distributed model is incorporated into structure changes Discrete Dynamic
In the parameter learning of Bayesian network, so as to be effectively reduced to a certain extent parameter learning process to big-sample data according to
Rely so that the variable structure discrete dynamic bayesian networks after parameter learning obtain accurate reasoning knot under Small Sample Database
Fruit.Wherein, expertise can be obtained by building Di Li Crays (Dirichlet) distributed model or beta (Beta) distributed model
Distributed model.
In embodiments of the present invention, in variable structure discrete dynamic bayesian networks, can according to the evidences of observer nodes (or
Value) forward inference obtains the evidence of concealed nodes.According to the sample number that sensor collects on the evidence of concealed nodes, unmanned plane
According to this and expertise distributed model collection sample, the parameter of variable structure discrete dynamic bayesian networks can be optimized,
The variable structure discrete dynamic bayesian networks trained.
Sliding-mode surface construction unit 33, for building the initial tracking error of default UAS model, according to initially with
Track error builds Time-dependent sliding surface.
Control law construction unit 34, for building time-varying sliding formwork control ratio according to the Time-dependent sliding surface of structure, so that nobody
The track of machine system model is maintained on Time-dependent sliding surface.
In embodiments of the present invention, UAS model is represented by:
Wherein, ξ=[x y z]T∈R3For the center of gravity of unmanned plane under inertial coodinate system
Position, V=[vx vy vz]T∈R3For the linear velocity of unmanned plane under inertial coodinate system, m is the quality of unmanned plane, η=[φ θ ψ
]TFor the attitude vectors of unmanned plane under inertial coodinate system, φ, θ and ψ are respectively roll angle, the angle of pitch and yaw angle, Ω=[p q
r]TFor the angular speed under unmanned plane body axis system, p, q, r are respectively angular velocity in roll, rate of pitch and yaw rate,
J∈R3×3For the moment of inertia matrix under unmanned plane body axis system, H is the attitude vectors conversion under unmanned plane body axis system
Matrix, FLFor the total life of four rotors of unmanned plane, FDFor the drag overall of four rotors of unmanned plane, ΓfThe liter being subject to for unmanned plane
Force square, ΓaThe Pneumatic friction torque being subject to for unmanned plane.
In embodiments of the present invention, the gesture stability target of unmanned plane is:In the case where unmanned plane perturbating upper bound is unknown,
Robust Control Law is designed, with by controlling fuselage deflection angle δ=[δφ,δθ,δψ]TRealize the attitude angle in being instructed to flight attitudeIt is tracked, that is, has:
Set up, wherein,For system tracking error, δφ、δθ、
δψThe respectively deflection angle of roll angle, the angle of pitch and yaw angle, φc、θcWithThe rolling of attitude angle respectively in flight attitude instruction
Corner, the angle of pitch and yaw angle.
In embodiments of the present invention, can be in traditional sliding formwork in order to eliminate the arrival section of traditional sliding formwork, ensure global robustness
On the basis of face, add an exponential term related to the initial tracking error of system so that UAS model from it is initial when
Quarter is on sliding-mode surface.Obtained Time-dependent sliding surface is built to be represented by:
Wherein, Ae-atFor the exponential term related to the initial tracking error of system, a ∈ R+Determine
Time-dependent sliding surface to when not variable sliding-surface velocity of approach, A ∈ R3For the parameter matrix related to unmanned plane original state, use
To ensure S (0)=03×1, can be calculatedΛ is parameter preset.According to what is built
Time-dependent sliding surface structure time-varying sliding formwork control ratio (i.e. Robust Control Law):
Wherein, η=diag { η1,η2,η3It is handoff gain matrix,
And meet ηj> Δs υjmax, Δ υjmaxFor Δ υjMaximum, whenWhen,WhenWhen, sat (sj(t))=sgn (sj(t)),For the boundary layer thickness of Time-dependent sliding surface, j=1,2,3.
Controller construction unit 35, for building sliding mode controller according to time-varying sliding formwork control ratio, and build sliding formwork observation
Device, the calculating that sliding mode observer is used for time-varying sliding formwork control ratio carry out noise processed.
In embodiments of the present invention, sliding mode controller is built according to time-varying sliding formwork control ratio, sliding mode controller is represented by:
Wherein, z1=δ is attitude angle vector.
In embodiments of the present invention, sliding mode observer is built according to time-varying sliding formwork control ratio, sliding mode observer is represented by:
Wherein, r1、r2、r3For observer parameter and r1,r2,r3∈R+,Respectively z1And z2Observation,For polymerization disturbance Δ υ estimate.By the expression formula of time-varying sliding formwork control ratio
Understand, when designing time-varying sliding formwork control ratio, it is necessary to use UAV Attitude angular derivative information, and because attitude angle is made an uproar
The influence of sound, high-frequency noise can be introduced by directly carrying out derivation to attitude angle, so as to be obtained by constructing high_order sliding mode control device
Required attitude angle derivative information, and the polymerization disturbance to time-varying sliding formwork control ratio is estimated, so as to effectively improve nobody
The precision of machine flight attitude control.
Information acquisition unit 36, for by default sensor on unmanned plane, gathering the flight at unmanned plane current time
Information.
In embodiments of the present invention, (or the more mesh visible rays of default monocular visible light sensor on unmanned plane can be passed through
Sensor), infrared light transducer[sensor, RGBD sensors, laser range finder, barometer and alignment system etc., collection unmanned plane is worked as
The flight information at preceding moment, flight information may include visual information, position, height and flight attitude of unmanned plane etc., so as to
It is follow-up to be flown according to the flight information collected control unmanned plane avoiding obstacles.
Posture generation unit 37, for flight information to be arranged to the observation data of default Bayesian network, pass through pattra leaves
This network generates the flight attitude information of unmanned plane subsequent time, and Bayesian network is to combine default expertise distributed model instruction
The variable structure discrete dynamic bayesian networks got.
In embodiments of the present invention, Bayesian network is to combine the change that default expertise distributed model trains to obtain
Structural separation dynamic bayesian network.Flight information can be arranged to the observation data of structure changes dynamic bayesian network, passed through
Adaptive reasoning algorithm in variable structure discrete dynamic bayesian networks, the flight attitude information of unmanned plane subsequent time is generated,
So that unmanned plane avoids the barrier in environment.
In embodiments of the present invention, the network structure of variable structure discrete dynamic bayesian networks can be divided into three layers:Bottom is
Observer nodes, the evidence of observer nodes are the flight information that sensor collects;The second layer is concealed nodes, and concealed nodes are nothing
Man-machine environmental situation assesses node, for assessing interference type, interference strength and the unmanned plane in unmanned plane local environment
With the relative distance of barrier etc.;Top layer is decision node, i.e., carries out decision-making to the flight attitude information of unmanned plane subsequent time,
For example, before interference in the environment occurs, decision node includes two class states, that is, passes through or hide, interference in the environment goes out
After now, decision node includes three class states, that is, advance-hide, stop-hiding, retreat-hide, with according in concealed nodes
Varying environment assess and different modes are carried out to the interference in environment hidden.Variable structure discrete dynamic bayesian networks finally push away
Manage the flight attitude information of the state, i.e. unmanned plane subsequent time of obtained decision node.
Instruction sending unit 38, for flight attitude information to be sent into the earth station associated with unmanned plane, pass through ground
Stand and flight attitude information is translated as flight attitude instruction, and the flight attitude instruction that satellite receiver returns.
In embodiments of the present invention, the flight attitude information that will be obtained by variable structure discrete dynamic bayesian networks reasoning
The earth station associated with unmanned plane is sent to, earth station's flight attitude according to corresponding to generating the flight attitude information instructs, and
Flight attitude instruction is returned into unmanned plane, so that unmanned plane is according to the tune of the flight attitude of return instruction progress flight attitude
It is whole.
Flight control units 39, for being referred to according to the default sliding mode controller with Time-dependent sliding surface and flight attitude
Order, the flight to unmanned plane are controlled.
In embodiments of the present invention, the sliding mode controller with Time-dependent sliding surface is pre-designed, to pass through the sliding formwork control
To nothing when device is to solve the problems, such as that traditional sliding formwork control reaches stage robustness deficiency, while eliminate the selection of sliding mode controller parameter
Man-machine upper bound is known to be required.Flight attitude instruction is carried out by the sliding mode controller with Time-dependent sliding surface
Reason, realize the flight control to unmanned plane.
In embodiments of the present invention, after the flight information at unmanned plane current time is collected, Bayesian network pair is passed through
The flight information is handled, and generates the flight attitude information of unmanned plane subsequent time, will by the earth station associated with unmanned plane
The flight attitude information is translated as flight attitude instruction, according to the default sliding mode controller with Time-dependent sliding surface and the flight
Attitude command, the flight to unmanned plane are controlled, so as to the structure changes dynamic discrete Bayesian network by combining expertise
Network, state of flight of the unmanned plane under complex dynamic environment is made inferences, pass through the sliding formwork control mould with Time-dependent sliding surface
Type is effectively tracked to the flight path of unmanned plane, is effectively improved the robustness and precision of UAV Flight Control,
So that the stability that unmanned plane flies in complex dynamic environment is stronger.
In embodiments of the present invention, each unit of the attitude-control device of unmanned plane can be by corresponding hardware or software unit
Realize, each unit can be independent soft and hardware unit, can also be integrated into a soft and hardware unit, herein not limiting
The present invention.
Example IV:
Fig. 4 shows the structure for the unmanned plane that the embodiment of the present invention four provides, and for convenience of description, illustrate only and this hair
The related part of bright embodiment.
The unmanned plane 4 of the embodiment of the present invention includes processor 40, memory 41 and is stored in memory 41 and can be
The computer program 42 run on processor 40.The processor 40 is realized in the above method embodiment when performing computer program 42
The step of, such as the step S101 to S104 shown in Fig. 1.Or realized during the execution computer program 42 of processor 40 above-mentioned each
The function of each unit in device embodiment, such as the function of unit 21 to 24 shown in Fig. 2.
In embodiments of the present invention, after the flight information at unmanned plane current time is collected, Bayesian network pair is passed through
The flight information is handled, and generates the flight attitude information of unmanned plane subsequent time, will by the earth station associated with unmanned plane
The flight attitude information is translated as flight attitude instruction, according to the default sliding mode controller with Time-dependent sliding surface and the flight
Attitude command, the flight to unmanned plane are controlled, so as to the structure changes dynamic discrete Bayesian network by combining expertise
Network, state of flight of the unmanned plane under complex dynamic environment is made inferences, pass through the sliding formwork control mould with Time-dependent sliding surface
Type is effectively tracked to the flight path of unmanned plane, is effectively improved the robustness and precision of UAV Flight Control,
So that the stability that unmanned plane flies in complex dynamic environment is stronger.
Embodiment five:
In embodiments of the present invention, there is provided a kind of computer-readable recording medium, the computer-readable recording medium are deposited
Computer program is contained, the computer program realizes the step in the above method embodiment when being executed by processor, for example, Fig. 1
Shown step S101 to S104.Or the computer program realize when being executed by processor it is each in above-mentioned each device embodiment
The function of unit, such as the function of unit 21 to 24 shown in Fig. 2.
In embodiments of the present invention, after the flight information at unmanned plane current time is collected, Bayesian network pair is passed through
The flight information is handled, and generates the flight attitude information of unmanned plane subsequent time, will by the earth station associated with unmanned plane
The flight attitude information is translated as flight attitude instruction, according to the default sliding mode controller with Time-dependent sliding surface and the flight
Attitude command, the flight to unmanned plane are controlled, so as to the structure changes dynamic discrete Bayesian network by combining expertise
Network, state of flight of the unmanned plane under complex dynamic environment is made inferences, pass through the sliding formwork control mould with Time-dependent sliding surface
Type is effectively tracked to the flight path of unmanned plane, is effectively improved the robustness and precision of UAV Flight Control,
So that the stability that unmanned plane flies in complex dynamic environment is stronger.
The computer-readable recording medium of the embodiment of the present invention can include that any of computer program code can be carried
Entity or device, recording medium, for example, the memory such as ROM/RAM, disk, CD, flash memory.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement made within refreshing and principle etc., should be included in the scope of the protection.
Claims (10)
1. a kind of attitude control method of unmanned plane, it is characterised in that methods described comprises the steps:
By default sensor on unmanned plane, the flight information at the unmanned plane current time is gathered;
The flight information is arranged to the observation data of default Bayesian network, the nothing is generated by the Bayesian network
The flight attitude information of man-machine subsequent time, the Bayesian network combine default expertise distributed model and train to obtain
Variable structure discrete dynamic bayesian networks;
The flight attitude information is sent to the earth station associated with the unmanned plane, by the earth station by the flight
Attitude information is translated as flight attitude instruction, and receives the flight attitude instruction that the earth station returns;
Instructed according to the default sliding mode controller with Time-dependent sliding surface and the flight attitude, the flight to the unmanned plane
It is controlled.
2. the method as described in claim 1, it is characterised in that by default sensor on unmanned plane, collection it is described nobody
Before the step of flight information at machine current time, methods described also includes:
The sample data of the unmanned plane during flying is gathered by the sensor on the unmanned plane, and builds the expertise point
Cloth model and the Bayesian network;
It is right according to the evidence of concealed nodes in the sample data, the expertise distributed model and the Bayesian network
The parameter of the Bayesian network optimizes, and generates the Bayesian network trained.
3. the method as described in claim 1, it is characterised in that by default sensor on unmanned plane, collection it is described nobody
Before the step of flight information at machine current time, methods described also includes:
The initial tracking error of the default UAS model of structure, the time-varying sliding formwork is built according to the initial tracking error
Face;
Time-varying sliding formwork control ratio is built according to the Time-dependent sliding surface of the structure, so that the track of the UAS model is protected
Hold on the Time-dependent sliding surface;
The sliding mode controller is built according to the time-varying sliding formwork control ratio, and builds sliding mode observer, the sliding mode observer
Noise processed is carried out for the calculating to the time-varying sliding formwork control ratio.
4. the method as described in claim 1, it is characterised in that the Bayesian network include observer nodes, concealed nodes and
Decision node, the observer nodes are the flight information of sensor collection, and the concealed nodes are the ring of the unmanned plane
Border Situation Assessment node, it is described after producing that the decision node includes the flight attitude of the unmanned plane and interference before interference produces
The flight attitude of unmanned plane.
5. a kind of attitude-control device of unmanned plane, it is characterised in that described device includes:
Information acquisition unit, for by default sensor on unmanned plane, the flight for gathering the unmanned plane current time to be believed
Breath;
Posture generation unit, for the flight information to be arranged to the observation data of default Bayesian network, pass through the shellfish
This network of leaf generates the flight attitude information of the unmanned plane subsequent time, and the Bayesian network is to combine default expertise
Distributed model trains obtained variable structure discrete dynamic bayesian networks;
Instruction sending unit, for the flight attitude information to be sent into the earth station associated with the unmanned plane, pass through institute
State earth station and the flight attitude information is translated as flight attitude instruction, and receive the flight appearance that the earth station returns
State instructs;And
Flight control units, for being instructed according to the default sliding mode controller with Time-dependent sliding surface and the flight attitude,
Flight to the unmanned plane is controlled.
6. device as claimed in claim 5, it is characterised in that described device also includes:
Network model construction unit, for gathering the sample number of the unmanned plane during flying by the sensor on the unmanned plane
According to, and build the expertise distributed model and the Bayesian network;And
Network training unit, for according in the sample data, the expertise distributed model and the Bayesian network
The evidence of concealed nodes, the parameter of the Bayesian network is optimized, generate the Bayesian network trained.
7. device as claimed in claim 5, it is characterised in that described device also includes:
Sliding-mode surface construction unit, for building the initial tracking error of default UAS model, according to the initial tracking
Error builds the Time-dependent sliding surface;
Control law construction unit, for building time-varying sliding formwork control ratio according to the Time-dependent sliding surface of the structure, so that the nothing
The track of model of man-machine system is maintained on the Time-dependent sliding surface;And
Controller construction unit, for building the sliding mode controller according to the time-varying sliding formwork control ratio, and build sliding formwork sight
Device is surveyed, the calculating that the sliding mode observer is used for the time-varying sliding formwork control ratio carries out noise processed.
8. device as claimed in claim 5, it is characterised in that the Bayesian network include observer nodes, concealed nodes and
Decision node, the observer nodes are the flight information of sensor collection, and the concealed nodes are the ring of the unmanned plane
Border Situation Assessment node, it is described after producing that the decision node includes the flight attitude of the unmanned plane and interference before interference produces
The flight attitude of unmanned plane.
9. a kind of unmanned plane, including memory, processor and it is stored in the memory and can transports on the processor
Capable computer program, it is characterised in that realize that Claims 1-4 such as is appointed described in the computing device during computer program
The step of one methods described.
10. a kind of computer-readable recording medium, the computer-readable recording medium storage has computer program, and its feature exists
In when the computer program is executed by processor the step of realization such as any one of Claims 1-4 methods described.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710778431.4A CN107703953B (en) | 2017-09-01 | 2017-09-01 | Attitude control method and device for unmanned aerial vehicle, unmanned aerial vehicle and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710778431.4A CN107703953B (en) | 2017-09-01 | 2017-09-01 | Attitude control method and device for unmanned aerial vehicle, unmanned aerial vehicle and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107703953A true CN107703953A (en) | 2018-02-16 |
CN107703953B CN107703953B (en) | 2020-10-23 |
Family
ID=61171378
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710778431.4A Active CN107703953B (en) | 2017-09-01 | 2017-09-01 | Attitude control method and device for unmanned aerial vehicle, unmanned aerial vehicle and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107703953B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108427289A (en) * | 2018-04-27 | 2018-08-21 | 哈尔滨工业大学 | A kind of hypersonic aircraft tracking and controlling method based on nonlinear function |
CN110333737A (en) * | 2019-07-05 | 2019-10-15 | 湖北理工学院 | A kind of high unmanned aerial vehicle control system of spraying efficiency for pesticide spraying and method |
CN112904866A (en) * | 2021-01-28 | 2021-06-04 | 西安建筑科技大学 | Inspection robot warehousing charging control method and system and outdoor inspection robot |
CN113641181A (en) * | 2020-04-27 | 2021-11-12 | 华中科技大学 | Aircraft gain self-adaptive attitude control method and system based on online performance evaluation |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2010008639A1 (en) * | 2008-04-09 | 2010-01-21 | Christopher William Weller | Intelligent jungle canopy surveillance appartus and method |
US20100235034A1 (en) * | 2009-03-16 | 2010-09-16 | The Boeing Company | Method, Apparatus And Computer Program Product For Recognizing A Gesture |
CN102426806A (en) * | 2011-11-07 | 2012-04-25 | 同济大学 | Regional rail network UAV cruise method based on dynamic cell division |
CN103472850A (en) * | 2013-09-29 | 2013-12-25 | 合肥工业大学 | Multi-unmanned aerial vehicle collaborative search method based on Gaussian distribution prediction |
WO2015147715A1 (en) * | 2014-03-28 | 2015-10-01 | Telefonaktiebolaget L M Ericsson (Publ) | Method and device for controlling an autonomous device |
CN106155054A (en) * | 2016-07-05 | 2016-11-23 | 中国科学院深圳先进技术研究院 | Wheel carries out control system and the method for composite mobile robot |
US20170153650A1 (en) * | 2015-11-30 | 2017-06-01 | Metal Industries Research & Development Centre | Multiple rotors aircraft and control method |
CN106802658A (en) * | 2017-03-21 | 2017-06-06 | 厦门大学 | Method for rapidly positioning in a kind of full-automatic high precision room |
-
2017
- 2017-09-01 CN CN201710778431.4A patent/CN107703953B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2010008639A1 (en) * | 2008-04-09 | 2010-01-21 | Christopher William Weller | Intelligent jungle canopy surveillance appartus and method |
US20100235034A1 (en) * | 2009-03-16 | 2010-09-16 | The Boeing Company | Method, Apparatus And Computer Program Product For Recognizing A Gesture |
CN102426806A (en) * | 2011-11-07 | 2012-04-25 | 同济大学 | Regional rail network UAV cruise method based on dynamic cell division |
CN103472850A (en) * | 2013-09-29 | 2013-12-25 | 合肥工业大学 | Multi-unmanned aerial vehicle collaborative search method based on Gaussian distribution prediction |
WO2015147715A1 (en) * | 2014-03-28 | 2015-10-01 | Telefonaktiebolaget L M Ericsson (Publ) | Method and device for controlling an autonomous device |
US20170153650A1 (en) * | 2015-11-30 | 2017-06-01 | Metal Industries Research & Development Centre | Multiple rotors aircraft and control method |
CN106155054A (en) * | 2016-07-05 | 2016-11-23 | 中国科学院深圳先进技术研究院 | Wheel carries out control system and the method for composite mobile robot |
CN106802658A (en) * | 2017-03-21 | 2017-06-06 | 厦门大学 | Method for rapidly positioning in a kind of full-automatic high precision room |
Non-Patent Citations (2)
Title |
---|
BARKLEY BRETT E,等: "cooperative bayesian target detection on a real road network using aerial vehicles", 《2016 ICUAS》 * |
张松,等: "基于模糊自适应终端滑模的飞行器姿态跟踪控制", 《自动化技术与应用》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108427289A (en) * | 2018-04-27 | 2018-08-21 | 哈尔滨工业大学 | A kind of hypersonic aircraft tracking and controlling method based on nonlinear function |
CN108427289B (en) * | 2018-04-27 | 2021-06-29 | 哈尔滨工业大学 | Hypersonic aircraft tracking control method based on nonlinear function |
CN110333737A (en) * | 2019-07-05 | 2019-10-15 | 湖北理工学院 | A kind of high unmanned aerial vehicle control system of spraying efficiency for pesticide spraying and method |
CN113641181A (en) * | 2020-04-27 | 2021-11-12 | 华中科技大学 | Aircraft gain self-adaptive attitude control method and system based on online performance evaluation |
CN113641181B (en) * | 2020-04-27 | 2023-05-26 | 华中科技大学 | Aircraft gain self-adaptive attitude control method and system based on online performance evaluation |
CN112904866A (en) * | 2021-01-28 | 2021-06-04 | 西安建筑科技大学 | Inspection robot warehousing charging control method and system and outdoor inspection robot |
CN112904866B (en) * | 2021-01-28 | 2023-04-21 | 西安建筑科技大学 | Warehouse-in charging control method and system for inspection robot and outdoor inspection robot |
Also Published As
Publication number | Publication date |
---|---|
CN107703953B (en) | 2020-10-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Choi et al. | Unmanned aerial vehicles using machine learning for autonomous flight; state-of-the-art | |
Qiu et al. | Receding horizon control for multiple UAV formation flight based on modified brain storm optimization | |
CN107703953A (en) | A kind of attitude control method of unmanned plane, device, unmanned plane and storage medium | |
Yan et al. | Fixed-Wing UAVs flocking in continuous spaces: A deep reinforcement learning approach | |
Bernardini et al. | Planning the behaviour of low-cost quadcopters for surveillance missions | |
CN108549407A (en) | A kind of control algolithm of multiple no-manned plane collaboration formation avoidance | |
CN106705970A (en) | Multi-UAV(Unmanned Aerial Vehicle) cooperation path planning method based on ant colony algorithm | |
CN106054922A (en) | Unmanned aerial vehicle (UAV)-unmanned ground vehicle (UGV) combined formation cooperative control method | |
Scorsoglio et al. | Image-based deep reinforcement learning for autonomous lunar landing | |
CN109669475A (en) | Multiple no-manned plane three-dimensional formation reconfiguration method based on artificial bee colony algorithm | |
CN110928189A (en) | Robust control method based on reinforcement learning and Lyapunov function | |
CN113848974B (en) | Aircraft trajectory planning method and system based on deep reinforcement learning | |
CN104977938A (en) | Fixed-dimensionality flying type multi-rotor aircraft and flying control method | |
CN109856972A (en) | A kind of unmanned helicopter robust Fault-Tolerant tracking and controlling method | |
Harik et al. | Fuzzy logic controller for predictive vision-based target tracking with an unmanned aerial vehicle | |
CN114169066A (en) | Space target characteristic measuring and reconnaissance method based on micro-nano constellation approaching reconnaissance | |
Ferdaus et al. | Development of c-means clustering based adaptive fuzzy controller for a flapping wing micro air vehicle | |
CN108398885B (en) | Rotor flying mechanical arm self_adaptive RBF NNs surveys Auto-disturbance-rejection Control of making an uproar | |
Niu et al. | UAV track planning based on evolution algorithm in embedded system | |
Ma et al. | Target tracking control of UAV through deep reinforcement learning | |
CN113848984B (en) | Unmanned aerial vehicle cluster control method and system | |
Zijian et al. | Imaginary filtered hindsight experience replay for UAV tracking dynamic targets in large-scale unknown environments | |
Deshpande et al. | Developmental reinforcement learning of control policy of a quadcopter UAV with thrust vectoring rotors | |
Li et al. | A survey of indoor uav obstacle avoidance research | |
CN113674310B (en) | Four-rotor unmanned aerial vehicle target tracking method based on active visual perception |
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 |