CN109062248A - Space non-cooperative target appearance rail integration method for parameter estimation based on self-organizing network - Google Patents
Space non-cooperative target appearance rail integration method for parameter estimation based on self-organizing network Download PDFInfo
- Publication number
- CN109062248A CN109062248A CN201810872909.4A CN201810872909A CN109062248A CN 109062248 A CN109062248 A CN 109062248A CN 201810872909 A CN201810872909 A CN 201810872909A CN 109062248 A CN109062248 A CN 109062248A
- Authority
- CN
- China
- Prior art keywords
- cooperative target
- self
- space non
- parameter estimation
- parameter
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000010354 integration Effects 0.000 title claims abstract description 18
- 230000009977 dual effect Effects 0.000 claims abstract description 33
- 238000013528 artificial neural network Methods 0.000 claims abstract description 19
- 210000002569 neuron Anatomy 0.000 claims description 13
- 230000004913 activation Effects 0.000 claims description 12
- 238000005259 measurement Methods 0.000 claims description 12
- 230000000644 propagated effect Effects 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000013519 translation Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 230000001808 coupling effect Effects 0.000 abstract description 4
- 238000013461 design Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 6
- 230000006872 improvement Effects 0.000 description 4
- 238000006073 displacement reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64G—COSMONAUTICS; VEHICLES OR EQUIPMENT THEREFOR
- B64G1/00—Cosmonautic vehicles
- B64G1/22—Parts of, or equipment specially adapted for fitting in or to, cosmonautic vehicles
- B64G1/24—Guiding or controlling apparatus, e.g. for attitude control
- B64G1/244—Spacecraft control systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Navigation (AREA)
Abstract
The invention discloses a kind of space non-cooperative target appearance rail integration method for parameter estimation based on self-organizing network.The parameter estimation algorithm carries out kinematics and dynamics modeling to space non-cooperative target by dual vector quaternary number, and designs corresponding self-organizing network parameter estimation algorithm on this basis.The characteristic that dual vector quaternary number is utilized in entire parameter estimation algorithm has carried out integrated estimation to the appearance rail parameter of space non-cooperative target, it is contemplated that the appearance rail coupling effect of space non-cooperative target.Meanwhile this parameter estimation algorithm devises the self organizing neural network with three layers of hidden layer, can carry out parameter Estimation to space non-cooperative target in the case where measuring failure condition to make the parameter estimation algorithm have stronger robustness to space environment.
Description
Technical field
The invention belongs to space technology field more particularly to a kind of space non-cooperative target appearance rails based on self-organizing network
Integrated method for parameter estimation.
Background technique
Growing space junk has seriously affected the normal solar-system operation of the mankind.Especially growing is each
Class failure spacecraft does not only take up a large amount of track resources, and has great threat to space safety.In recent years each spacefaring nation and
International research mechanism has reached widespread consensus: in order to guarantee the utilizability of track resources and the safety in space, it is necessary to
To the space junk in space, especially failure spacecraft is removed.In the process, since failure spacecraft cannot provide
Self information and free to tumble is carried out in space.Therefore, it is carried out accurate parameter Estimation to subsequent parameter identification with
And arrest control it is particularly significant.
Traditional base is mainly utilized to the work of actively removing of failure spacecraft this kind space non-cooperative target at this stage
It is modeled in the kinematical equation of quaternary number and traditional relative dynamics equation, and Kalman filtering class is based on using tradition
Method carry out space non-cooperative target parameter Estimation.However, due to space complicated in appearance rail coupling effect and space
The case where environment can cause larger interference to measurement sensor, in the case where metrical information failure, the method for this quasi-tradition is simultaneously
Accurate reliable appearance rail integration parameter Estimation cannot be carried out to space non-cooperative target.
Summary of the invention
The purpose of the present invention is to solve the above problems existing for existing space non-cooperative target parameter Estimation, provide
A kind of space non-cooperative target appearance rail integration method for parameter estimation based on self-organizing network, the design of this parameter estimation algorithm
Self organizing neural network with three layers of hidden layer can carry out parameter to space non-cooperative target in the case where measuring failure condition and estimate
Meter is to make the parameter estimation algorithm have stronger robustness to space environment.
To achieve the above object, technical scheme is as follows:
A kind of space non-cooperative target appearance rail integration method for parameter estimation based on self-organizing network, including following step
It is rapid:
Based on dual vector quaternary number, Relative Kinematics are established using error equation, it is opposite to consider that product of inertia is established
Kinetics equation；
When measurement metrical information of the sensor in relation to space non-cooperative target of Servicing spacecraft is effective, Servicing spacecraft
Parameter Estimation is carried out to space non-cooperative target using expanded Kalman filtration algorithm；
When the measurement sensor of Servicing spacecraft is in relation to the failure of the metrical information of space non-cooperative target, Servicing spacecraft
The parameter of space non-cooperative target is estimated using the space non-cooperative target method for parameter estimation based on self-organizing network；
Meanwhile the result after estimation being used to reset extended Kalman filter.
As a further improvement of the present invention, the step of establishing relative dynamics equation specifically: pass through turning target
It is dynamic to consider simultaneously with translation, and related rotation and translation parameter dual vector quaternary number parametrization are obtained with specific object
Manage the relative parameter of meaning；Meanwhile it being based on dual vector quaternary number, Relative Kinematics are established using error equation, are considered
Product of inertia establishes relative dynamics equation.
As a further improvement of the present invention, the kinematics model based on dual vector quaternary number are as follows:
Kinetic model based on dual vector quaternary number are as follows:
Wherein:For error dual vector quaternary number,For the estimator of relative velocity dual vector quaternary number,For
Relative velocity dual vector quaternary number,
As a further improvement of the present invention, it when the measuring device of Servicing spacecraft can not export effective measurement, adopts
With containing there are three the self organizing artificial neural networks of hidden layer, and by artificial neural network to the parameter of space non-cooperative target into
Row appearance rail integration estimation, estimated value is for resetting extended Kalman filter.
As a further improvement of the present invention, self organizing neural network includes three hidden layers, is respectively:
Self-organization layer is used for propagated forward information, promotes the dynamic characteristic of network, and activation primitive is tansig function；
Feedback layer, every group of neuron include two neurons, and two neurons constitute unity feedback, are used for storage network
Information, activation primitive are f=sigmoid function；
Self-organization layer is used for propagated forward information, promotes the dynamic characteristic of network, and activation primitive is tansig function；
Output layer, activation primitive are purelin function；
δ algorithm off-line training of the neural network based on error；After the completion of training, in the case where measuring effective situation,
The network carries out real-time update in space.
The invention has the benefit that
A kind of space non-cooperative target appearance rail integration parameter Estimation side based on self-organizing network proposed by the invention
Method is modeled using kinematics and dynamics of the dual vector quaternary number to space non-cooperative target, to consider appearance rail coupling
Effect is closed, integrated estimation can be accomplished to the appearance rail parameter of space non-cooperative target, conventional Extension is used when measuring effective
Kalman filtering carries out appearance rail integration parameter Estimation；When measuring failure, using the parameter Estimation side based on self-organizing network
Method estimates the parameter of space non-cooperative target, and resets extended Kalman filter, thus enable parameter Estimation according to
It is old that the parameter of space non-cooperative target is effectively estimated in the case where measuring failure.Entire parameter estimation algorithm is utilized
The characteristic of dual vector quaternary number has carried out integrated estimation to the appearance rail parameter of space non-cooperative target, it is contemplated that the non-conjunction in space
Make the appearance rail coupling effect of target.Meanwhile this parameter estimation algorithm devises the self organizing neural network with three layers of hidden layer, energy
It is enough that parameter Estimation is carried out to make the parameter estimation algorithm to space environment to space non-cooperative target in the case where measuring failure condition
With stronger robustness.
Detailed description of the invention
Fig. 1 is the schematic diagram of Servicing spacecraft and space non-cooperative target；
Fig. 2 is the schematic diagram of self organizing neural network structure；
Fig. 3 is that self organizing neural network structure estimates space non-cooperative target progress parameter in conjunction with Extended Kalman filter
The schematic diagram of the algorithm of meter；
Specific embodiment
A kind of parameter Estimation side of the space non-cooperative target appearance rail integration method for parameter estimation based on self-organizing network
Method is a kind of mixed parameter estimation method.When measurement metrical information of the sensor in relation to space non-cooperative target of Servicing spacecraft
When effective, Servicing spacecraft carries out parameter Estimation to space non-cooperative target using traditional expanded Kalman filtration algorithm；When
When the measurement sensor of Servicing spacecraft is in relation to the failure of the metrical information of space non-cooperative target, Servicing spacecraft uses a kind of base
The parameter of space non-cooperative target is estimated in the space non-cooperative target method for parameter estimation of self-organizing network.Meanwhile
Result after estimation is used for the resetting to extended Kalman filter.
When the measuring device of Servicing spacecraft can export effective measurement, for the movement based on dual vector quaternary number
Kinetic model and metrical information are learned, the appearance rail integration method for parameter estimation based on Extended Kalman filter is designed；
When the measuring device of Servicing spacecraft can not export effective measurement, design is containing there are three the self-organizing people of hidden layer
Artificial neural networks, and appearance rail integration estimation, estimation are carried out by parameter of the artificial neural network to space non-cooperative target
Value is for resetting extended Kalman filter.
Wherein, consider the space non-cooperative target kinematics Dynamic Modeling side based on dual vector quaternary number of product of inertia
Method carries out mathematical expression to the relative kinematic of space non-cooperative target, dynamics using dual vector quaternary number；It is wherein opposite
During dynamic (dynamical) mathematical expression, the product of inertia of space non-cooperative target is considered.
Modeling tool is dual vector quaternary number, by considering the rotation of target and translation simultaneously, and by related rotation
The relative parameter with specific physical meaning is obtained with translation parameter dual vector quaternary number parametrization.Meanwhile being based on this
A little dual vector quaternary numbers, establish Relative Kinematics using error equation；Consider that product of inertia establishes relative dynamics equation.
Kinematics and dynamics model based on dual vector quaternary number is as follows:
Kinematics model based on dual vector quaternary number:
Kinetic model based on dual vector quaternary number:
Wherein:For error dual vector quaternary number,For the estimator of relative velocity dual vector quaternary number,For
Relative velocity dual vector quaternary number,
Below in conjunction with attached drawing to the present invention into detailed description:
Fig. 1 is the schematic diagram of Servicing spacecraft and space non-cooperative target.Wherein 1 is space non-cooperative target, and 2 be service
Spacecraft, 3 be target observation point, and { I } is inertial system；{ B } is target this system, and origin is in target centroid；{ B'} is observation point
Coordinate system, it is assumed that known to its installation matrix with target this system and be parallel to target this system, ρ is observation point and target centroid
Between displacement.rB/IFor the displacement of the sensor on target centroid and Servicing spacecraft, rmFor in observation point and Servicing spacecraft
Sensor displacement.
Fig. 2 is the schematic diagram of self organizing neural network structure.The self organizing neural network includes three hidden layers, is respectively:
10 neurons are contained altogether in self-organization layer 21, are used for propagated forward information, promote the dynamic characteristic of network, activation primitive is
Tansig function；Feedback layer contains 5 groups of neurons altogether, and every group of neuron includes two neurons, and two neurons are constituted
Unity feedback, is used for storage network information, and activation primitive is f=sigmoid function；10 neurons are contained altogether in self-organization layer 22,
For propagated forward information, the dynamic characteristic of network is promoted, activation primitive is tansig function.Output layer has 10 neurons,
Activation primitive is purelin function.δ algorithm off-line training of the neural network based on error.After the completion of training, measuring
In effective situation, which carries out real-time update in space.
Fig. 3 is that self organizing neural network structure estimates space non-cooperative target progress parameter in conjunction with Extended Kalman filter
The schematic diagram of the algorithm of meter, wherein 31 be the current time state (state initial value) of input, 32 is based on dual vector quaternary numbers
The state for time of model updates, and 33 be measurement fail-ure criterion, and 34 be the Extended Kalman filter parameter Estimation when measuring effective
Method, 35 be the self organizing neural network noncooperative target method for parameter estimation when measuring failure, and 36 be resetting next step shape
State value.
The above described is only a preferred embodiment of the present invention, limitation in any form not is done to the present invention, though
So the present invention has been disclosed above in the preferred embodiment, and however, it is not intended to limit the invention, any technology for being familiar with this profession
Personnel, without departing from the scope of the present invention, when the method and technique content using the disclosure above make it is a little
The equivalent embodiment of equivalent variations, but anything that does not depart from the technical scheme of the invention content are changed or are modified to, according to the present invention
Technical spirit any simple modification, equivalent change and modification made to the above embodiment, still belong to technical solution of the present invention
In range.
Claims (5)
1. a kind of space non-cooperative target appearance rail integration method for parameter estimation based on self-organizing network, which is characterized in that packet
Include following steps:
Based on dual vector quaternary number, Relative Kinematics are established using error equation, consider that product of inertia establishes opposite power
Learn equation；
When measurement metrical information of the sensor in relation to space non-cooperative target of Servicing spacecraft is effective, Servicing spacecraft is used
Expanded Kalman filtration algorithm carries out parameter Estimation to space non-cooperative target；
When the measurement sensor of Servicing spacecraft is in relation to the failure of the metrical information of space non-cooperative target, Servicing spacecraft is used
Space non-cooperative target method for parameter estimation based on self-organizing network estimates the parameter of space non-cooperative target；Together
When, the result after estimation is used to reset extended Kalman filter.
2. the space non-cooperative target appearance rail integration parameter Estimation side according to claim 1 based on self-organizing network
Method, which is characterized in that the step of establishing relative dynamics equation specifically: by the way that the rotation of target and translation are considered simultaneously,
And related rotation and translation parameter dual vector quaternary number parametrization are obtained into the relative parameter with specific physical meaning；
Meanwhile it being based on dual vector quaternary number, Relative Kinematics are established using error equation, consider that product of inertia establishes opposite power
Learn equation.
3. the space non-cooperative target appearance rail integration parameter Estimation according to claim 1 or 2 based on self-organizing network
Method, which is characterized in that
Kinematics model based on dual vector quaternary number are as follows:
Kinetic model based on dual vector quaternary number are as follows:
Wherein:For error dual vector quaternary number,For the estimator of relative velocity dual vector quaternary number,It is opposite
Speed dual vector quaternary number,
4. the space non-cooperative target appearance rail integration parameter Estimation side according to claim 1 based on self-organizing network
Method, which is characterized in that
When the measuring device of Servicing spacecraft can not export effective measurement, using manually refreshing containing the self-organizing there are three hidden layer
Appearance rail integration estimation is carried out through network, and by parameter of the artificial neural network to space non-cooperative target, estimated value is used for
Reset extended Kalman filter.
5. the space non-cooperative target appearance rail integration parameter Estimation side according to claim 4 based on self-organizing network
Method, which is characterized in that self organizing neural network includes three hidden layers, is respectively:
Self-organization layer is used for propagated forward information, promotes the dynamic characteristic of network, and activation primitive is tansig function；
Feedback layer, every group of neuron include two neurons, and two neurons constitute unity feedback, believe for storage network
Breath, activation primitive are f=sigmoid function；
Self-organization layer is used for propagated forward information, promotes the dynamic characteristic of network, and activation primitive is tansig function；
Output layer, activation primitive are purelin function；
δ algorithm off-line training of the neural network based on error；After the completion of training, in the case where measuring effective situation, the net
Network carries out real-time update in space.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810872909.4A CN109062248A (en) | 2018-08-02 | 2018-08-02 | Space non-cooperative target appearance rail integration method for parameter estimation based on self-organizing network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810872909.4A CN109062248A (en) | 2018-08-02 | 2018-08-02 | Space non-cooperative target appearance rail integration method for parameter estimation based on self-organizing network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109062248A true CN109062248A (en) | 2018-12-21 |
Family
ID=64832800
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810872909.4A Pending CN109062248A (en) | 2018-08-02 | 2018-08-02 | Space non-cooperative target appearance rail integration method for parameter estimation based on self-organizing network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109062248A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110470297A (en) * | 2019-03-11 | 2019-11-19 | 北京空间飞行器总体设计部 | A kind of attitude motion of space non-cooperative target and inertial parameter estimation method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014066981A1 (en) * | 2012-10-31 | 2014-05-08 | Resource Energy Solutions Inc. | Methods and systems for improved drilling operations using real-time and historical drilling data |
| CN104406605A (en) * | 2014-10-13 | 2015-03-11 | 中国电子科技集团公司第十研究所 | Aircraft-mounted multi-navigation-source comprehensive navigation simulation system |
| CN104406598A (en) * | 2014-12-11 | 2015-03-11 | 南京航空航天大学 | Non-cooperative spacecraft attitude estimation method based on virtual sliding mode control |
| CN106548475A (en) * | 2016-11-18 | 2017-03-29 | 西北工业大学 | A kind of Forecasting Methodology of the target trajectory that spins suitable for space non-cooperative |
| CN106570563A (en) * | 2015-10-13 | 2017-04-19 | 中国石油天然气股份有限公司 | Deformation prediction method and device based on Kalman filtering and BP neural network |
| CN107421541A (en) * | 2017-05-25 | 2017-12-01 | 西北工业大学 | A kind of morphological parameters measuring method of fault-tolerant contactless inert satellite |
-
2018
- 2018-08-02 CN CN201810872909.4A patent/CN109062248A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014066981A1 (en) * | 2012-10-31 | 2014-05-08 | Resource Energy Solutions Inc. | Methods and systems for improved drilling operations using real-time and historical drilling data |
| CN104406605A (en) * | 2014-10-13 | 2015-03-11 | 中国电子科技集团公司第十研究所 | Aircraft-mounted multi-navigation-source comprehensive navigation simulation system |
| CN104406598A (en) * | 2014-12-11 | 2015-03-11 | 南京航空航天大学 | Non-cooperative spacecraft attitude estimation method based on virtual sliding mode control |
| CN106570563A (en) * | 2015-10-13 | 2017-04-19 | 中国石油天然气股份有限公司 | Deformation prediction method and device based on Kalman filtering and BP neural network |
| CN106548475A (en) * | 2016-11-18 | 2017-03-29 | 西北工业大学 | A kind of Forecasting Methodology of the target trajectory that spins suitable for space non-cooperative |
| CN107421541A (en) * | 2017-05-25 | 2017-12-01 | 西北工业大学 | A kind of morphological parameters measuring method of fault-tolerant contactless inert satellite |
Non-Patent Citations (2)
| Title |
|---|
| 张建民，等: "《智能控制原理及应用》", 28 February 2003, 北京：冶金工业出版社 * |
| 德黑兰尼，等: "《非线性***故障的混合方法》", 31 October 2014, 北京：国防工业出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110470297A (en) * | 2019-03-11 | 2019-11-19 | 北京空间飞行器总体设计部 | A kind of attitude motion of space non-cooperative target and inertial parameter estimation method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109284530A (en) | Space non-cooperative target appearance rail integration method for parameter estimation based on deep learning | |
| AU2021101247A4 (en) | Human-in-the-Loop Consensus Control for High-Rise Firefighting Multi-MUAV Systems with Unknown Disturbances and Actuator Failures | |
| CN105700555B (en) | A kind of multiple no-manned plane collaboratively searching method based on gesture game | |
| CN109343341A (en) | It is a kind of based on deeply study carrier rocket vertically recycle intelligent control method | |
| CN108803316A (en) | For the Active Fault-tolerant Control Method of multi-agent system actuator failures | |
| CN107422741B (en) | Learning-based cluster flight distributed attitude tracking control method for preserving preset performance | |
| CN110275436A (en) | A kind of RBF neural self-adaptation control method of more single arm robots | |
| CN108873687A (en) | A kind of Intelligent Underwater Robot behavior system knot planing method based on depth Q study | |
| CN107598897A (en) | A kind of method of humanoid robot gait's planning based on human body teaching | |
| CN108333949A (en) | For the sliding formwork fault tolerant control method of multi-agent system actuator partial failure failure | |
| CN109032137A (en) | More Euler-Lagrange system distributed tracking control methods | |
| CN108196453A (en) | A kind of manipulator motion planning Swarm Intelligent Computation method | |
| CN106647771A (en) | Multi-mobile-robot minimum step formation method | |
| CN110631592B (en) | Indoor autonomous navigation AGV (automatic guided vehicle) motion track fusion method based on LSTM (least squares metric model) | |
| CN112959330B (en) | Robot double-arm motion man-machine corresponding device and method based on master-slave dynamic motion elements | |
| CN109828467A (en) | A kind of the unmanned boat intensified learning controller architecture and design method of data-driven | |
| CN112859915A (en) | High-rise fire-fighting unmanned aerial vehicle formation control method and system based on saturation threshold event triggering | |
| CN112527015A (en) | Fire-fighting unmanned aerial vehicle formation sliding film control method based on event triggering | |
| CN109062248A (en) | Space non-cooperative target appearance rail integration method for parameter estimation based on self-organizing network | |
| CN114083539A (en) | Mechanical arm anti-interference motion planning method based on multi-agent reinforcement learning | |
| CN108445894A (en) | A kind of secondary paths planning method considering unmanned boat movenent performance | |
| CN113885548A (en) | Many four rotor unmanned aerial vehicle output restraint state unanimous game controller | |
| Li et al. | Maritime buoyage inspection system based on an unmanned aerial vehicle and active disturbance rejection control | |
| CN115185187B (en) | Mechanical arm limited time tracking control method based on type-II ellipsoidal fuzzy neural network | |
| CN113359626B (en) | Finite time hierarchical control method for multi-robot system |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181221 |