CN103412488B - A kind of miniature self-service gyroplane high-accuracy control method based on adaptive neural network - Google Patents
A kind of miniature self-service gyroplane high-accuracy control method based on adaptive neural network Download PDFInfo
- Publication number
- CN103412488B CN103412488B CN201310347956.4A CN201310347956A CN103412488B CN 103412488 B CN103412488 B CN 103412488B CN 201310347956 A CN201310347956 A CN 201310347956A CN 103412488 B CN103412488 B CN 103412488B
- Authority
- CN
- China
- Prior art keywords
- neural network
- miniature self
- adaptive neural
- adaptive
- control
- 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
Landscapes
- Feedback Control In General (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
A kind of miniature self-service gyroplane high-accuracy control method based on adaptive neural network is related to miniature self-service gyroplane feedback control, the Composite Controller Design that the structure for the adaptive neural network that no specimen is trained is combined with optimization.First, for miniature self-service gyroplane kinetic model, feedback control coefficient matrix is built by pole-assignment to ensure the primary stability of system；Secondly, designing has the adaptive neural network of autonomous update weights characteristic, builds adaptive network right value update matrix come the weight matrix of online updating neural network based on control information, realizes estimation and inhibition to disturbance；And design adaptive threshold optimisation strategy, error mean square based on physical location and desired locations in time window is poor, online updating is carried out to the control residual error upper limit threshold of adaptive neural network, reduce the influence of control residual error upper bound lax pair neural network disturbance controlled quentity controlled variable, and then optimize adaptive neural network and disturb controlled quentity controlled variable, realize the miniature self-service gyroplane high-precision attitude control under complex environment.The present invention has many advantages, such as that real-time is good, dynamic parameter response is fast, interferes adaptable, the high-precision control that can be used under miniature self-service gyroplane complexity multi-source interference environment to multi-source.
Description
Technical field
The present invention relates to a kind of miniature self-service gyroplane high-accuracy control method based on adaptive neural network, is suitable for
Work skyborne unmanned robot autonomous control field.
Background technology
Miniature self-service gyroplane has the characteristics such as VTOL, hovering, can be by self-contained various kinds of sensors
The tasks such as the narrow spaces such as danger zone or drive execute observation, information is collected, are with a wide range of applications.With answering
Working environment with the expansion in field, miniature self-service gyroplane is also complicated and changeable, the miniature self-service rotation that vulnerability to jamming is strong, stability is high
Wing machine high-precision control becomes the hot spot of research.
As complicated multi-input multi-output control system, miniature self-service gyroplane has non-linear, close coupling, control difficult
Spend high characteristic.And miniature self-service gyroplane in flight course there are multiclass interference, as wind is disturbed, atmospheric turbulance, ground are dry
It disturbs, system electromagnetic interference etc., therefore, high-precision control of the miniature self-service gyroplane under disturbance is the key technology of flight control system
One of.
To improve performance, all kinds of control methods such as intelligent PID control method, robust control, intelligent control method are used for
The flight of miniature self-service gyroplane controls.Intelligent PID controller is simple in structure, but poor anti jamming capability, miniature self-service gyroplane
Control performance be highly susceptible to external interference influence and reduce.Robust control can preferably eliminate miniature self-service gyroplane and exist
Model parameter present in flight course inaccurately and external interference problem, but robust control have real-time it is poor, dynamic ginseng
The characteristic of number low-response.By a large amount of sample training, nonlinear autoregressive may be implemented in neural network, overcomes small-sized nothing
Model uncertainty possessed by people's gyroplane, and the problems such as there are multi-source interference, realize high-precision gesture stability, but pass
The neural network of system needs a large amount of sample data to be trained, and has the shortcomings that real-time is poor.
Invention content
The technology of the present invention solves the problems, such as：For miniature self-service gyroplane in the task of execution control performance be easy by
The problem of external interference influences proposes a kind of complex controll side being combined based on adaptive neural network and pole-assignment
Method is estimated and is inhibited to the suffered multi-source interference awing of miniature self-service gyroplane, realizes the high-precision of big envelope range
Degree control.
Technical solution of the invention is：For miniature self-service gyroplane kinetic model, pass through pole-assignment
Feedback control coefficient matrix is built to ensure the primary stability of system；Designing has the adaptive god of autonomous update weights characteristic
Through network, adaptive network right value update matrix is built come the weight matrix of online updating neural network, in fact based on control information
Now to the estimation of disturbance and inhibition；And design adaptive threshold optimisation strategy, based in time window physical location and expectation
The error mean square of position is poor, carries out online updating to the control residual error upper limit threshold of adaptive neural network, realizes complex environment
Under miniature self-service gyroplane high-precision attitude control.Implementation step is as follows：
(1) it is directed to miniature self-service gyroplane kinetic model, feedback control coefficient matrix is built by pole-assignment
To ensure the primary stability of system；
(2) to in-flight existing multi-source interference, the adaptive neural network with autonomous update weights characteristic, base are designed
Carry out the weight matrix of online updating neural network in control information structure adaptive network right value update matrix, realizes to small-sized nothing
Awing suffered multi-source interference carries out On-line Estimation to people's gyroplane, and adaptive neural network right value update matrix and disturbance are estimated
It is as follows to measure expression formula：
Wherein,For the weight matrix of adaptive neural network,For the disturbance estimator of adaptive neural network；Γi、
P is symmetric positive definite matrix, the input e=x-x of adaptive neural networkdIt is expected state variable xdBetween virtual condition variable x
Error, B are miniature self-service gyroplane state of a control transfer matrix, αwFor the control residual error upper limit threshold of adaptive neural network,
I* is i-th of row vector of corresponding matrix, and * i are i-th of column vector of corresponding matrix, and s (e) is implicit for adaptive neural network
The node function of layer, is defined as Gaussian function, the node function expression formula of corresponding j-th of hidden layer is as follows：
Wherein, μj,Respectively the central value and width of adaptive neural network hidden layer Gaussian function, l are adaptive
The implicit number of nodes of neural network hidden layer；
(3) adaptive threshold optimisation strategy is designed, the error based on physical location and desired locations in time window is equal
Variance carries out online updating to the control residual error upper limit threshold of adaptive neural network, realizes the miniature self-service under complex environment
Gyroplane high-precision attitude controls.
The miniature self-service gyroplane high-accuracy control method based on adaptive neural network of the present invention, wherein the step
(3) structure adaptive threshold optimisation strategy is defined as follows
α in formulawFor the control residual error upper limit threshold of adaptive neural network in the actual time window sampling period；αw-1For
The control residual error upper limit threshold of adaptive neural network in a upper window sample period time；αw-2It is sampled for upper two time window
The control residual error upper limit threshold of adaptive neural network in period；χkFor miniature self-service rotor in a upper window sample period time
Machine physical location xxmWith desired locations xxdMean square deviation；χk-tIt is real for miniature self-service gyroplane in the upper two time windows sampling period
Border position xxmWith desired locations xxdMean square deviation；eeiFor miniature self-service gyroplane physical location in the time window sampling period
xxmWith desired locations xxdDifference；T is sampling number in the time window sampling period；k1Parameter in order to control, η1,η2When respectively
Between miniature self-service gyroplane physical location xx in the window sample periodmWith desired locations xxdMaximum absolute error value and average mistake
Difference.
The advantages of the present invention over the prior art are that：
(1) present invention ensures the primary stability of system building feedback control coefficient matrix by pole-assignment
On the basis of, the adaptive neural network trained by no specimen, the suffered disturbance in flight course to miniature self-service gyroplane
Estimated and inhibited have the advantages that strong interference immunity and convenient for design；
(2) present invention further utilizes adaptive neural network in the case where traditional feedback control ensures that system is stablized
The disturbance estimated and inhibit miniature self-service gyroplane suffered in flight course, can be in real time according to the status information tune of aircraft
Not only there is whole rudder amount characteristic simple in structure and easy to control, dynamic parameter good with period control method real-time to respond soon,
It disclosure satisfy that high-precision control demand under miniature self-service gyroplane load environment；
(3) present invention only requires according to the status information acquired during miniature self-service gyroplane practical flight, it is based on solution
Obtained site error, so that it may with the weights of online updating adaptive neural network, not need any sample training, there is number
According to acquisition convenience, calculate simple advantage.
Description of the drawings
Fig. 1 is miniature self-service gyroplane autonomous control flow；
Fig. 2 is disturbed for 3.2m/s wind and is executed four destination cruising flight effects using miniature self-service gyroplane of the present invention under environment.
Specific implementation mode
As shown in Figure 1, the concrete methods of realizing of the present invention is as follows：
(1) feedback control based on POLE PLACEMENT USING
Based on linearization technique, miniature self-service gyroplane kinetics equation is expressed as
Wherein, state variable x ∈ RnIndicate the corresponding speed of miniature self-service gyroplane system, angle and angular velocity information.
Control variable u ∈ RmRespectively represent the lateral feathering of miniature self-service gyroplane, longitudinal feathering, always away from control signal and boat
To control signal；A∈Rn×nWith B ∈ Rn×mThe respectively state-transition matrix of state variable and control variable and control transfer square
Battle array；d∈RmExpression disturbed by wind, atmospheric turbulance, ground interference, system electromagnetic interference, sensor measurement errors, and by small-sized nothing
People's gyroplane systematic parameter is uncertain and the bounded composite interference brought without factors such as mode kinetic characteristics.
The controller input of miniature self-service gyroplane is made of two parts, a part of to be that feedback of status inputs Kx (t),
Another part is that adaptive neural network disturbs estimatorAs
Wherein, feedback factor K is obtained according to POLE PLACEMENT USING theory, to ensure the primary stability of system；
(2) adaptive neural network is built
To in-flight existing multi-source interference, designing, there is the adaptive neural network of autonomous update weight matrix to improve
The control accuracy of system realizes that awing suffered multi-source interference carries out On-line Estimation and inhibition to miniature self-service gyroplane.
Adaptive neural network is made of input layer, hidden layer and output layer；The input layer of adaptive neural network it is defeated
Enter it is expected state variable xdError between virtual condition variable x, i.e. e=x-xd；
Hidden layer is made of multiple Gaussian functions, is defined as s (e), the node function expression formula of corresponding j-th of hidden layer
It is as follows：
Wherein, μj,Respectively the central value and width of adaptive neural network hidden layer Gaussian function, l are adaptive
The implicit number of nodes of neural network hidden layer, the central value μ of adaptive radial base neural net nodej, widthIt is determined by user
It is fixed.
The estimator that adaptive output layer interferes multi-source
Wherein,For the weight matrix of adaptive neural network；Γi, P be symmetric positive definite matrix, αwFor adaptive neural network net
The control residual error upper limit threshold of network, i* are i-th of row vector of corresponding matrix, and * i are i-th of column vector of corresponding matrix, wherein
The weight matrix of adaptive neural network is independently updated according to following rule
Wherein P is following formula equation positive definite solution
(A+BK)TP+P (A+BK)=- Q
Wherein symmetric positive definite matrix Q=I.
(3) adaptive threshold optimisation strategy is designed
Error mean square based on physical location and desired locations in time window is poor, the control to adaptive neural network
Residual error upper limit threshold carries out online updating, realizes the miniature self-service gyroplane high-precision attitude control under complex environment.
Adaptive threshold optimisation strategy is defined as follows：
α in formulawFor the control residual error upper limit threshold of adaptive neural network in the actual time window sampling period；αw-1For
The control residual error upper limit threshold of adaptive neural network in a upper window sample period time；αw-2It is sampled for upper two time window
The control residual error upper limit threshold of adaptive neural network in period；χkFor miniature self-service rotor in a upper window sample period time
Machine physical location xxmWith desired locations xxdMean square deviation；χk-tIt is real for miniature self-service gyroplane in the upper two time windows sampling period
Border position xxmWith desired locations xxdMean square deviation；eeiFor miniature self-service gyroplane physical location in the time window sampling period
xxmWith desired locations xxdDifference；T is sampling number in the time window sampling period；k1Parameter in order to control, η1,η2When respectively
Between miniature self-service gyroplane physical location xx in the window sample periodmWith desired locations xxdMaximum absolute error value and average mistake
Difference.
(5) flight example
The verification of four destination flight experiments is carried out based on miniature self-service gyroplane.Four destination patrol flights are fixed 20 meters high, with boat
Point (10, -20,20) is starting point, passes through destination (40, -20,20) respectively, (40,0,20) and (10,0,20) are final to hover
In starting point.The comparison of feedback and adaptive neural network control method based on identical feedback control matrix parameter
The results are shown in Figure 2, and in the case where the most strong wind of 3.2m/s disturbs environment, the miniature self-service gyroplane based on adaptive neural network is being held
Crimping precision when four destination line walking task of row is 1.56m, is 0.83 m in the crimping precision of hovering phase, better than traditional
Feedback.
The present invention is based on the miniature self-service gyroplane high-accuracy control methods of adaptive neural network to overcome existing control
The complicated high-precision flight controls etc. disturbed under environment of miniature self-service gyroplane may be implemented in the deficiency of method more.
The content that description in the present invention is not described in detail belongs to the prior art well known to professional and technical personnel in the field.
Claims (2)
1. a kind of miniature self-service gyroplane high-accuracy control method based on adaptive neural network, it is characterised in that realize following
Step：
(1) it is directed to miniature self-service gyroplane kinetic model, feedback control coefficient matrix is built by pole-assignment to protect
The primary stability of card system；
(2) to in-flight existing multi-source interference, design has the adaptive neural network of autonomous update weights characteristic, based on mistake
Poor information architecture adaptive network right value update matrix carrys out the weight matrix of online updating neural network, realizes and is revolved to miniature self-service
The suffered multi-source interference awing of wing machine carries out On-line Estimation, adaptive neural network right value update matrix and disturbance estimation scale
It is as follows up to formula：
Wherein,For the weight matrix of adaptive neural network,For the disturbance estimator of adaptive neural network；Γi, P be pair
Claim positive definite matrix, the input e=x-x of adaptive neural networkdIt is expected state variable xdError between virtual condition variable x,
B is miniature self-service gyroplane state of a control transfer matrix, αwFor the control residual error upper limit threshold of adaptive neural network, i* is phase
It is i-th of column vector of corresponding matrix to answer i-th of row vector of matrix, * i, and s (e) is the section of adaptive neural network hidden layer
Point function, is defined as Gaussian function, and the node function expression formula of corresponding j-th of hidden layer is as follows：
Wherein, μj,Respectively the central value and width of adaptive neural network hidden layer Gaussian function, l are adaptive neural network
The implicit number of nodes of network hidden layer；
(3) adaptive threshold optimisation strategy is designed, the error mean square based on physical location and desired locations in time window is poor,
Online updating is carried out to the control residual error upper limit threshold of adaptive neural network, realizes the miniature self-service gyroplane under complex environment
High-precision attitude controls.
2. the miniature self-service gyroplane high-accuracy control method according to claim 1 based on adaptive neural network,
It is characterized in that：Step (3) the structure adaptive threshold optimisation strategy is defined as follows:
α in formulawFor the control residual error upper limit threshold of adaptive neural network in the actual time window sampling period；αw-1For upper a period of time
Between in the window sample period adaptive neural network control residual error upper limit threshold；αw-2For in the upper two time windows sampling period
The control residual error upper limit threshold of adaptive neural network；χkIt is practical for miniature self-service gyroplane in a upper window sample period time
Position xxmWith desired locations xxdMean square deviation；χk-tFor miniature self-service gyroplane physical location in the upper two time windows sampling period
xxmWith desired locations xxdMean square deviation；eeiFor miniature self-service gyroplane physical location xx in the time window sampling periodmWith the phase
Hope position xxdDifference；T is sampling number in the time window sampling period；k1Parameter in order to control, η1,η2Respectively time window
Miniature self-service gyroplane physical location xx in sampling periodmWith desired locations xxdMaximum absolute error value and average error value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310347956.4A CN103412488B (en) | 2013-08-12 | 2013-08-12 | A kind of miniature self-service gyroplane high-accuracy control method based on adaptive neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310347956.4A CN103412488B (en) | 2013-08-12 | 2013-08-12 | A kind of miniature self-service gyroplane high-accuracy control method based on adaptive neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103412488A CN103412488A (en) | 2013-11-27 |
| CN103412488B true CN103412488B (en) | 2018-10-30 |
Family
ID=49605513
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310347956.4A Active CN103412488B (en) | 2013-08-12 | 2013-08-12 | A kind of miniature self-service gyroplane high-accuracy control method based on adaptive neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103412488B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104865829B (en) * | 2015-03-26 | 2017-06-23 | 哈尔滨工业大学 | Multi-robot system distributed self-adaption neutral net continuous tracking control method of electro |
| CN104880945B (en) * | 2015-03-31 | 2018-05-29 | 成都市优艾维机器人科技有限公司 | The adaptive inverse control of rotor wing unmanned aerial vehicle based on neutral net |
| CN105785762B (en) * | 2016-03-17 | 2020-12-11 | 北京航空航天大学 | Two-axis inertially stabilized platform high-precision control method based on self-adaptive backstepping sliding mode |
| CN105843243B (en) * | 2016-05-06 | 2019-02-22 | 深圳一电航空技术有限公司 | Control method, device and the multi-rotor aerocraft of multi-rotor aerocraft |
| CN106094518B (en) * | 2016-06-22 | 2018-12-21 | 北京航空航天大学 | A kind of structural vibration pole placement control method based on Multidisciplinary systems optimization |
| CN106682733B (en) * | 2016-11-07 | 2018-10-19 | 上海资誉电子科技有限公司 | Unmanned plane motion state analysis method and device |
| CN110832408B (en) * | 2017-07-03 | 2022-03-25 | 深圳市大疆创新科技有限公司 | Neural network based image target tracking by aircraft |
| CN108032994A (en) * | 2017-12-06 | 2018-05-15 | 余姚市荣事特电子有限公司 | A kind of unmanned helicopter |
| CN107985569A (en) * | 2017-12-06 | 2018-05-04 | 余姚市荣事特电子有限公司 | A kind of unmanned plane |
| CN108563124B (en) * | 2018-04-26 | 2021-01-05 | 宋永端 | Self-adaptive control method of rotor unmanned aerial vehicle based on API (application program interface) user-settable track |
| CN109375642B (en) * | 2018-09-20 | 2021-06-22 | 太原理工大学 | Energy-saving control method for unmanned aerial vehicle |
| CN112445238B (en) * | 2020-11-19 | 2021-09-10 | 西南大学 | Unmanned aerial vehicle tracking system based on neural network |
| CN113267998B (en) * | 2021-03-19 | 2024-02-02 | 北京航空航天大学 | High-precision modeling and control method for atomic gyroscope temperature control system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07277286A (en) * | 1994-04-11 | 1995-10-24 | Mitsubishi Heavy Ind Ltd | Learning flight control device for aircraft |
| EP0901053A1 (en) * | 1997-09-04 | 1999-03-10 | Rijksuniversiteit te Groningen | Method for modelling and/or controlling a production process using a neural network and controller for a production process |
| US6092919A (en) * | 1995-08-01 | 2000-07-25 | Guided Systems Technologies, Inc. | System and method for adaptive control of uncertain nonlinear processes |
| US6185470B1 (en) * | 1997-11-07 | 2001-02-06 | Mcdonnell Douglas Corporation | Neural network predictive control method and system |
| CN102289714A (en) * | 2011-06-02 | 2011-12-21 | 北京航空航天大学 | Method for controlling autonomous take-off and landing of small unmanned rotorcraft based on behavioral model |
| CN102385316A (en) * | 2011-09-16 | 2012-03-21 | 哈尔滨工程大学 | Deepening controlling method of underactuated automatic underwater vehicle based on neural network back stepping method |
| CN102411305A (en) * | 2011-11-11 | 2012-04-11 | 南京航空航天大学 | Design method of comprehensive disturbance rejection control system for single-rotor wing helicopter/turboshaft engine |
-
2013
- 2013-08-12 CN CN201310347956.4A patent/CN103412488B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07277286A (en) * | 1994-04-11 | 1995-10-24 | Mitsubishi Heavy Ind Ltd | Learning flight control device for aircraft |
| US6092919A (en) * | 1995-08-01 | 2000-07-25 | Guided Systems Technologies, Inc. | System and method for adaptive control of uncertain nonlinear processes |
| EP0901053A1 (en) * | 1997-09-04 | 1999-03-10 | Rijksuniversiteit te Groningen | Method for modelling and/or controlling a production process using a neural network and controller for a production process |
| US6185470B1 (en) * | 1997-11-07 | 2001-02-06 | Mcdonnell Douglas Corporation | Neural network predictive control method and system |
| CN102289714A (en) * | 2011-06-02 | 2011-12-21 | 北京航空航天大学 | Method for controlling autonomous take-off and landing of small unmanned rotorcraft based on behavioral model |
| CN102385316A (en) * | 2011-09-16 | 2012-03-21 | 哈尔滨工程大学 | Deepening controlling method of underactuated automatic underwater vehicle based on neural network back stepping method |
| CN102411305A (en) * | 2011-11-11 | 2012-04-11 | 南京航空航天大学 | Design method of comprehensive disturbance rejection control system for single-rotor wing helicopter/turboshaft engine |
Non-Patent Citations (3)
| Title |
|---|
| Neural networks as a tool for the assessment of human pilot behavkmr in wind shear;D. Martens 等;《Aerospace Science and Technology》;19991231;第39-48页 * |
| The errors in simultaneous approximation by feed-forward neural networks;Tingfan Xie 等;《Neurocomputing》;20100131;第903-907页 * |
| 无人旋翼飞行器自适应飞行控制***设计与仿真;夏青元 等;《机器人》;20130131;第35卷(第1期);第98-106页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103412488A (en) | 2013-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103412488B (en) | A kind of miniature self-service gyroplane high-accuracy control method based on adaptive neural network | |
| Cheng et al. | Real-time optimal control for spacecraft orbit transfer via multiscale deep neural networks | |
| CN107479567B (en) | The unknown quadrotor drone attitude controller of dynamic characteristic and method | |
| Lin | Distributed UAV formation control using differential game approach | |
| CN110806759B (en) | Aircraft route tracking method based on deep reinforcement learning | |
| CN103885450B (en) | Depopulated helicopter attitude nonlinear control method and verification platform | |
| Islam et al. | Robust control of four-rotor unmanned aerial vehicle with disturbance uncertainty | |
| CN105353615B (en) | A kind of Active Fault-tolerant Control Method of the quadrotor based on sliding mode observer | |
| CN105607473B (en) | The attitude error Fast Convergent self-adaptation control method of small-sized depopulated helicopter | |
| CN109696830B (en) | Reinforced learning self-adaptive control method of small unmanned helicopter | |
| CN104199295B (en) | Electromechanical servo system friction compensation and variable structure control method based on neural network | |
| CN105912009B (en) | Four-rotor aircraft control method based on pole allocation and fuzzy active disturbance rejection control technology | |
| CN105785762A (en) | Bi-axis inertially-stabilized platform high-precision control method based on self-adaptive backstepping sliding mode | |
| CN104950901B (en) | Depopulated helicopter attitude error finite time convergence control nonlinear robust control method | |
| Chen et al. | Robust trajectory tracking control for a quadrotor using recursive sliding mode control and nonlinear extended state observer | |
| CN102289714B (en) | Method for controlling autonomous take-off and landing of small unmanned rotorcraft based on behavioral model | |
| CN103853050A (en) | PID optimization control method of four-rotor aircraft | |
| CN105138001A (en) | Attitude control method of four-rotor aircraft | |
| CN106647584A (en) | Fault tolerant control method of four-rotor-wing aircraft based on optimal sliding mode | |
| CN108594837A (en) | Model-free quadrotor drone contrail tracker and method based on PD-SMC and RISE | |
| CN110320925A (en) | Quadrotor method of controlling security based on high-order interference observer | |
| CN109683624A (en) | Nonlinear robust control method for small-sized depopulated helicopter gesture stability | |
| CN104932514A (en) | Posture nonlinear self-adaptive control method for small unmanned helicopter | |
| Li et al. | Aggressive online control of a quadrotor via deep network representations of optimality principles | |
| Wang et al. | Robust attitude tracking control of small-scale unmanned helicopter |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |