CN111830848A - Unmanned aerial vehicle super-maneuvering flight performance simulation training system and method - Google Patents
Unmanned aerial vehicle super-maneuvering flight performance simulation training system and method Download PDFInfo
- Publication number
- CN111830848A CN111830848A CN202010760894.XA CN202010760894A CN111830848A CN 111830848 A CN111830848 A CN 111830848A CN 202010760894 A CN202010760894 A CN 202010760894A CN 111830848 A CN111830848 A CN 111830848A
- Authority
- CN
- China
- Prior art keywords
- flight
- neural network
- unmanned aerial
- aerial vehicle
- module
- 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
- 238000012549 training Methods 0.000 title claims abstract description 57
- 238000004088 simulation Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims description 29
- 238000013528 artificial neural network Methods 0.000 claims abstract description 77
- 230000009471 action Effects 0.000 claims abstract description 29
- 230000015654 memory Effects 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 15
- 239000007787 solid Substances 0.000 claims description 7
- 238000011161 development Methods 0.000 claims description 5
- 238000013461 design Methods 0.000 claims description 4
- 230000002860 competitive effect Effects 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000013500 data storage Methods 0.000 description 2
- 230000007787 long-term memory Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000006386 memory function Effects 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000036544 posture Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B17/00—Systems involving the use of models or simulators of said systems
- G05B17/02—Systems involving the use of models or simulators of said systems electric
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an unmanned aerial vehicle super-maneuver flight performance simulation training system, which comprises a computing module, a storage module, a neural network computing module, a maneuver flight controller, a flight simulation display module and a multi-input module, wherein the computing module is used for generating a simulation model; the multi-input module is used for collecting a plurality of groups of specific maneuvering action time sequences based on the X-Plane flying environment; the storage module is used for storing the sequence; the neural network computing module is used for fitting and training the sequence based on a deep neural network architecture to generate a maneuvering action deep neural network; the maneuvering flight controller is used for generating maneuvering action instructions on line based on the maneuvering action deep neural network according to the current flight state; and the flight simulation display module is used for displaying the simulated flight of the unmanned aerial vehicle in real time through X-plane flight simulation software. The invention has the advantages of self-adaptive maneuvering simulation flight and simulation demonstration under the condition of a complex wind field, high maneuvering action instruction real-time performance and reliability and the like.
Description
Technical Field
The invention relates to the technical field of unmanned aerial vehicles, in particular to a system and a method for simulating and training super-maneuvering flight performance of an unmanned aerial vehicle.
Background
Currently, the main military uses of drones include reconnaissance, drone, aerial relay, ground strike, interference, and electronic countermeasure, among others. With the development of technology and the need for new military combat, unmanned planes directly engaged in air combat are also beginning to be scheduled. Moreover, due to the fact that physical condition limitation of pilots is not available, the unmanned aerial vehicle can achieve ultrahigh maneuvering actions which cannot be achieved by the unmanned aerial vehicle, and the unmanned aerial vehicle has obvious advantages in aerial combat. Most of the existing unmanned aerial vehicle control systems stay in a stable flight stage, can only fly under limited rolling and pitching postures, and cannot exert the maneuvering performance of the unmanned aerial vehicle. With the expansion of the application range and the competition of the military field, the maneuvering flight becomes the key point of the future unmanned aerial vehicle technology development. Historically, research on unmanned aerial vehicles has focused on the realization of stable flight, and the research on maneuvering flight of unmanned aerial vehicles is less. The existing research relates to the aspects of simulated flight, actual flight test, control algorithm implementation and the like of various types of aircrafts, but the definition and description of the maneuvering action are not clear enough, and the engineering implementation of the autonomous maneuvering flight control has no representative solution.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: aiming at the technical problems in the prior art, the invention provides a system and a method for simulating and training the super-maneuvering flight performance of an unmanned aerial vehicle for self-adaptive simulated flight under the condition of a complex wind field.
In order to solve the technical problems, the invention adopts the technical scheme that:
an unmanned aerial vehicle super-maneuver flight performance simulation training system comprises a computing module, a storage module, a neural network computing module, a maneuver flight controller, a flight simulation display module and a multi-input module;
the multi-input module is used for acquiring a plurality of groups of specific maneuvering action time sequences by adopting a control lever or a remote controller based on an X-Plane flight environment;
the storage module is used for storing the sequence;
the neural network computing module is used for fitting and training the sequence based on a deep neural network architecture to generate a maneuvering action deep neural network;
the maneuvering flight controller is used for generating maneuvering action instructions on line based on the maneuvering action deep neural network according to the current flight state;
and the flight simulation display module is used for displaying the simulated flight of the unmanned aerial vehicle in real time through X-plane flight simulation software.
Preferably, the neural network computing module further comprises a neural network compensation unit, configured to establish a three-layer neural network structure to correct model errors and environmental interference; the three-layer neural network comprises an input layer, a hidden layer and an output layer, the output of each layer of neural network is fed back to the controlled variable, and the final control rate is designed as follows:
whereincIn order to control the quality of the quantity for the dynamic inversion,
for the neural network compensation result, v is a robust term, adjustedNeural network parameters to achieve stable flight of the aircraft.
Preferably, the neural network computing module adopts a CM1K neural network chip and a development system; the network chip is realized by 1024 hardware computing units, a daisy chain structure is formed by special buses, competitive learning is rapidly carried out among different hardware computing units, a newly-arrived input nearest unit is judged according to the distance, and updating of network weight and unit state are automatically carried out, so that storage and adjustment of knowledge are realized, and training of a neural network is finally realized.
Preferably, the intelligent layer module of the CM1K neural network chip is used as an operation platform for completing the maneuvering action deep neural network training and the data acquisition and training of the maneuvering action of the unmanned aerial vehicle.
Preferably, the plurality of sets of specific maneuvers time series comprise aircraft pitch, roll, yaw; pitch, roll, yaw rate, throttle amount, elevator, aileron rudder, rudder yaw.
Preferably, the storage module is a solid state disk.
The invention also discloses a training method used in the unmanned aerial vehicle super-maneuver flight performance simulation training system, which comprises the following steps:
1) collecting and storing a plurality of groups of specific maneuvering action time sequences by using a control lever or a remote controller based on an X-Plane flight environment;
2) fitting and training the sequence based on a deep neural network architecture to generate a maneuvering action deep neural network;
3) generating a maneuver instruction on line based on a maneuver deep neural network according to the current flight state;
4) and displaying the simulated flight of the unmanned aerial vehicle in real time through X-plane flight simulation software.
Preferably, in step 2), the memory module of the long-short term memory network stores and accesses previous information based on the design of the unique gate control unit by using the long-short term memory network method, so as to take existing training data and the current flight state into consideration, and generate a more accurate flight instruction.
The invention also discloses a computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, performs the steps of the training method as described above.
The invention further discloses a computer device comprising a memory and a processor, the memory having stored thereon a computer program, characterized in that the computer program, when executed by the processor, performs the steps of the training method as described above.
Compared with the prior art, the invention has the advantages that:
according to the simulation training system and method for the super-maneuvering flight performance of the unmanned aerial vehicle, the simulation flight data of the unmanned aerial vehicle is acquired, the neural network controller of the unmanned aerial vehicle is trained, and the neural network compensator of the adaptive control is trained, so that the adaptive maneuvering simulation flight and the simulation demonstration of the unmanned aerial vehicle under the condition of a complex wind field are finally completed; because the maneuver deep neural network has a memory function, the real-time performance and the reliability of the maneuver instruction generation can be ensured in the verification flight.
The invention relates to a system and a method for simulating and training the super-maneuvering flight performance of an unmanned aerial vehicle, which utilize a long-short term memory network (LSTM) method and are based on the unique design of a gate control unit, so that a memory module of the LSTM can store and access long-term former information, thereby giving consideration to the existing training data and the current flight state and generating a more accurate flight instruction.
The invention relates to a simulation training system and a simulation training method for super-maneuvering flight performance of an unmanned aerial vehicle, which are self-adaptive dynamic inverse methods based on neural network compensation, on one hand, compensate dynamic inverse control errors caused by inaccurate modeling, and can compensate attitude disturbance caused by external complex wind fields.
According to the simulation training system and method for the super-maneuver flight performance of the unmanned aerial vehicle, the high-speed solid state disk is used for storing data, and the data storage speed can be increased.
Drawings
FIG. 1 is a block diagram of an embodiment of the system of the present invention.
Fig. 2 is an interface diagram of the simulation flight data recording of the unmanned aerial vehicle in the invention.
FIG. 3 is a diagram of the results of flight data acquisition in accordance with the present invention.
Detailed Description
The invention is further described below with reference to the figures and the specific embodiments of the description.
As shown in fig. 1 to fig. 3, the unmanned aerial vehicle super-maneuver flight performance simulation training system of the embodiment includes a calculation module, a storage module, a neural network calculation module, a maneuver flight controller, a flight simulation display module, and a multi-input module; the multi-input module is used for acquiring a plurality of groups of specific maneuvering action time sequences by adopting a control lever or a remote controller based on the X-Plane flight environment; the storage module is used for storing the sequence; the neural network computing module is used for fitting and training the sequence based on a deep neural network architecture to generate a maneuvering action deep neural network; the maneuvering flight controller is used for generating maneuvering action instructions on line based on the maneuvering action deep neural network according to the current flight state; and the flight simulation display module is used for displaying the simulated flight of the unmanned aerial vehicle in real time through X-plane flight simulation software.
In this embodiment, the neural network computing module further includes a neural network compensation unit, configured to establish a three-layer neural network structure to correct model errors and environmental interference; the three-layer neural network comprises an input layer, a hidden layer and an output layer, the output of each layer of neural network is fed back to the controlled variable, and the final control rate is designed as follows: the final control rate is designed as:
whereincIn order to control the quality of the quantity for the dynamic inversion,
and v is a robust term for the neural network compensation result, and the stable flight of the aircraft is realized by adjusting the neural network parameters.
The unmanned aerial vehicle super-maneuver flight performance simulation training system can be used for unmanned aerial vehicle simulation flight data acquisition, unmanned aerial vehicle neural network controller training and neural network compensator training for completing self-adaptive control, and finally completing unmanned aerial vehicle maneuver flight and simulation demonstration.
In this embodiment, the deep neural network instruction architecture and the adaptive neural network compensator have a high requirement on the computation speed in training. In order to realize online neural network calculation, a CM1K neural network chip and a development system are utilized. The network chip is realized by 1024 hardware computing units, a daisy chain structure can be formed by a special bus, competitive learning can be rapidly carried out among different units, a newly-arrived input nearest unit is judged according to the distance, and updating of network weight and unit state are automatically carried out, so that storage and adjustment of knowledge are realized, and training of a neural network is finally realized.
In this embodiment, the wisdom layer module of CM1K neural network chip is as operation platform, accomplishes the deep neural network training of maneuver to and the data acquisition and the training of unmanned aerial vehicle maneuver.
In this embodiment, the plurality of specific maneuvers time series include aircraft pitch, roll, and yaw; pitch, roll, yaw rate, throttle amount, elevators, aileron rudders, rudder yaw, etc.
In this embodiment, the storage module is a solid state disk; the data acquisition result is stored as a text file, and in order to improve the data storage speed, a high-speed solid state disk is adopted to store data.
The invention also discloses a training method used in the unmanned aerial vehicle super-maneuver flight performance simulation training system, aiming at realizing high maneuver flight of the unmanned aerial vehicle, aiming at different tactical templates, a brain-simulating controller and a training and learning method are adopted to automatically realize the control with little feedback or no feedback, and the method specifically comprises the following steps:
1) acquiring a plurality of groups of specific maneuvering action time sequences by using a control lever or a remote controller based on an X-Plane flight environment, and storing the time sequences, wherein the time sequences consist of characteristic parameters of maneuvering actions, such as pitching, rolling and yaw angles of an airplane; pitch, roll, yaw rate, throttle amount, elevators, aileron rudders, rudder yaw, etc.;
2) fitting and training the sequence based on a deep neural network architecture to generate a maneuvering action deep neural network;
3) after the maneuver deep neural network is trained, because the network has a memory function, a maneuver instruction can be generated on line based on the maneuver deep neural network according to the current flight state in the verification flight, so that the real-time performance and the reliability of the maneuver instruction generation are ensured;
4) and displaying the simulated flight of the unmanned aerial vehicle in real time through X-plane flight simulation software.
In this embodiment, in step 2), during fitting and training of the sequence based on the deep neural network architecture, since the state of the aircraft is different in the previous segment and the state of the aircraft entering the maneuver is different in the implementation process of the maneuver, the state that the aircraft should change at the next time is also different, and for the above problem, a long and short term memory network (LSTM) method is used, based on the design of its unique gate control unit, to enable the memory module of the long and short term memory network to store and access the previous information, and generate a more accurate flight instruction based on the existing training data and the current flight state.
As shown in fig. 2, in step 4), in the X-Plane flight simulation, data recording is performed at a speed of 99Hz, the data that can be recorded includes aircraft attitude, acceleration, position, control surface control amount, flight force and moment, wind field flow rate, and the like, and the data acquisition result is stored as a text file and stored on a high-speed solid state disk.
In the embodiment, in actual flight, the unmanned aerial vehicle is not only interfered by an external complex flow field, but also influenced by uncertainty of modeling, and particularly in super maneuvering flight, an aircraft model presents obvious nonlinear characteristics; therefore, an adaptive control mechanism is introduced into the bottom-layer execution mechanism; the system is a self-adaptive dynamic inverse method based on neural network compensation, on one hand, a neural network compensation module is used for compensating a dynamic inverse control error caused by inaccurate modeling, and can compensate attitude disturbance caused by an external complex wind field, so that stable flight of the unmanned aerial vehicle is realized, and the super-maneuvering flight simulation can be realized based on maneuvering action instructions generated by a neural network instruction framework and is further displayed in an X-Plane.
The invention also discloses a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, performs the steps of the training method as described above.
The invention further discloses a computer device comprising a memory and a processor, the memory having stored thereon a computer program which, when executed by the processor, performs the steps of the training method as described above.
All or part of the flow of the method of the embodiments may be implemented by a computer program, which may be stored in a computer-readable storage medium and executed by a processor, to implement the steps of the embodiments of the methods. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution media, and the like. The memory may be used to store computer programs and/or modules, and the processor may perform various functions by executing or executing the computer programs and/or modules stored in the memory, as well as by invoking data stored in the memory. The memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above-mentioned embodiments, and all technical solutions belonging to the idea of the present invention belong to the protection scope of the present invention. It should be noted that modifications and embellishments within the scope of the invention may be made by those skilled in the art without departing from the principle of the invention.
Claims (10)
1. An unmanned aerial vehicle super-maneuver flight performance simulation training system is characterized by comprising a computing module, a storage module, a neural network computing module, a maneuver flight controller, a flight simulation display module and a multi-input module;
the multi-input module is used for acquiring a plurality of groups of specific maneuvering action time sequences by adopting a control lever or a remote controller based on an X-Plane flight environment;
the storage module is used for storing the sequence;
the neural network computing module is used for fitting and training the sequence based on a deep neural network architecture to generate a maneuvering action deep neural network;
the maneuvering flight controller is used for generating maneuvering action instructions on line based on the maneuvering action deep neural network according to the current flight state;
and the flight simulation display module is used for displaying the simulated flight of the unmanned aerial vehicle in real time through X-plane flight simulation software.
2. The unmanned aerial vehicle super-maneuver flight performance simulation training system according to claim 1, wherein the neural network computing module further comprises a neural network compensation unit for establishing a three-layer neural network structure to correct model errors and environmental interference; the three-layer neural network comprises an input layer, a hidden layer and an output layer, the output of each layer of neural network is fed back to the controlled variable, and the final control rate is designed as follows:
whereincIn order to control the quality of the quantity for the dynamic inversion,
and v is a robust term for the neural network compensation result, and the stable flight of the aircraft is realized by adjusting the neural network parameters.
3. The unmanned aerial vehicle super mobile flight performance simulation training system of claim 2, wherein the neural network computing module employs a CM1K neural network chip and development system; the network chip is realized by 1024 hardware computing units, a daisy chain structure is formed by special buses, competitive learning is rapidly carried out among different hardware computing units, a newly-arrived input nearest unit is judged according to the distance, and updating of network weight and unit state are automatically carried out, so that storage and adjustment of knowledge are realized, and training of a neural network is finally realized.
4. The unmanned aerial vehicle super-maneuver flight performance simulation training system as claimed in claim 3, wherein the smart layer module of the CM1K neural network chip is used as an operation platform for performing maneuver deep neural network training and data acquisition and training of the maneuver of the unmanned aerial vehicle.
5. The unmanned aerial vehicle super-maneuver flight performance simulation training system according to any one of claims 1 to 4, wherein the plurality of groups of specific maneuver time sequences comprise airplane pitch, roll and yaw angles; pitch, roll, yaw rate, throttle amount, elevator, aileron rudder, rudder yaw.
6. The unmanned aerial vehicle super mobile flight performance simulation training system of any one of claims 1 to 4, wherein the storage module is a solid state disk.
7. A training method used in the unmanned aerial vehicle super-maneuver flight performance simulation training system of any one of claims 1 to 6, characterized by comprising the following steps:
1) collecting and storing a plurality of groups of specific maneuvering action time sequences by using a control lever or a remote controller based on an X-Plane flight environment;
2) fitting and training the sequence based on a deep neural network architecture to generate a maneuvering action deep neural network;
3) generating a maneuver instruction on line based on a maneuver deep neural network according to the current flight state;
4) and displaying the simulated flight of the unmanned aerial vehicle in real time through X-plane flight simulation software.
8. The training method as claimed in claim 7, wherein in step 2), the memory module of the long-short term memory network is enabled to store and access previous information based on the design of its unique gating unit by using the long-short term memory network method, so as to take into account the existing training data and the current flight state, and generate more accurate flight instructions.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the training method according to any one of claims 7 to 8.
10. A computer arrangement comprising a memory and a processor, the memory having stored thereon a computer program, characterized in that the computer program, when being executed by the processor, is adapted to carry out the steps of the training method according to any one of claims 7 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010760894.XA CN111830848A (en) | 2020-07-31 | 2020-07-31 | Unmanned aerial vehicle super-maneuvering flight performance simulation training system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010760894.XA CN111830848A (en) | 2020-07-31 | 2020-07-31 | Unmanned aerial vehicle super-maneuvering flight performance simulation training system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111830848A true CN111830848A (en) | 2020-10-27 |
Family
ID=72920743
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010760894.XA Pending CN111830848A (en) | 2020-07-31 | 2020-07-31 | Unmanned aerial vehicle super-maneuvering flight performance simulation training system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111830848A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113093568A (en) * | 2021-03-31 | 2021-07-09 | 西北工业大学 | Airplane automatic driving operation simulation method based on long-time and short-time memory network |
| CN113467512A (en) * | 2021-07-19 | 2021-10-01 | 宁波权智科技有限公司 | Unmanned aerial vehicle flying method and device based on neural network |
| WO2023184676A1 (en) * | 2022-04-01 | 2023-10-05 | 天津七一二通信广播股份有限公司 | Implementation method for unmanned aerial vehicle reinforcement learning training system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105159136A (en) * | 2015-07-23 | 2015-12-16 | 中国商用飞机有限责任公司北京民用飞机技术研究中心 | Flight simulation visual display method and system |
| CN107390545A (en) * | 2017-07-31 | 2017-11-24 | 彩虹无人机科技有限公司 | A kind of simulation training system of unmanned plane and its load |
| CN107679280A (en) * | 2017-09-04 | 2018-02-09 | 中国航空工业集团公司洛阳电光设备研究所 | It is a kind of that flight guiding algorithm exploitation verification method is looked squarely based on X Plane and Simulink |
| CN108304914A (en) * | 2017-01-12 | 2018-07-20 | 三星电子株式会社 | System and method for high-order shot and long term memory network |
| CN110348081A (en) * | 2019-06-26 | 2019-10-18 | 南京航空航天大学 | Based on the fighter plane HAOA characteristics analysis method up to balance collection |
-
2020
- 2020-07-31 CN CN202010760894.XA patent/CN111830848A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105159136A (en) * | 2015-07-23 | 2015-12-16 | 中国商用飞机有限责任公司北京民用飞机技术研究中心 | Flight simulation visual display method and system |
| CN108304914A (en) * | 2017-01-12 | 2018-07-20 | 三星电子株式会社 | System and method for high-order shot and long term memory network |
| CN107390545A (en) * | 2017-07-31 | 2017-11-24 | 彩虹无人机科技有限公司 | A kind of simulation training system of unmanned plane and its load |
| CN107679280A (en) * | 2017-09-04 | 2018-02-09 | 中国航空工业集团公司洛阳电光设备研究所 | It is a kind of that flight guiding algorithm exploitation verification method is looked squarely based on X Plane and Simulink |
| CN110348081A (en) * | 2019-06-26 | 2019-10-18 | 南京航空航天大学 | Based on the fighter plane HAOA characteristics analysis method up to balance collection |
Non-Patent Citations (1)
| Title |
|---|
| 喻煌超: "Adaptive Incremental Nonlinear Dynamic Inversion Control Based on Neural Network for UAV Maneuver", 《INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT MECHATRONICS》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113093568A (en) * | 2021-03-31 | 2021-07-09 | 西北工业大学 | Airplane automatic driving operation simulation method based on long-time and short-time memory network |
| CN113467512A (en) * | 2021-07-19 | 2021-10-01 | 宁波权智科技有限公司 | Unmanned aerial vehicle flying method and device based on neural network |
| WO2023184676A1 (en) * | 2022-04-01 | 2023-10-05 | 天津七一二通信广播股份有限公司 | Implementation method for unmanned aerial vehicle reinforcement learning training system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Punjani et al. | Deep learning helicopter dynamics models | |
| CN111830848A (en) | Unmanned aerial vehicle super-maneuvering flight performance simulation training system and method | |
| Kang et al. | Deep convolutional identifier for dynamic modeling and adaptive control of unmanned helicopter | |
| CN108445766A (en) | Model-free quadrotor drone contrail tracker and method based on RPD-SMC and RISE | |
| CN110794857B (en) | Robust discrete fractional order control method of fixed wing unmanned aerial vehicle considering external wind interference | |
| CN111766901B (en) | Multi-unmanned aerial vehicle cooperative target distribution attack method | |
| CN111176263A (en) | Online aircraft thrust fault identification method based on BP neural network | |
| CN115755956B (en) | Knowledge and data collaborative driving unmanned aerial vehicle maneuvering decision method and system | |
| Bierling | Comparative analysis of adaptive control techniques for improved robust performance | |
| CN109144099B (en) | Fast evaluation method for unmanned aerial vehicle group action scheme based on convolutional neural network | |
| CN111781942A (en) | Fault-tolerant flight control method based on self-constructed fuzzy neural network | |
| CN114329766A (en) | Flight dynamics model reliability evaluation method for deep reinforcement learning | |
| US11029709B1 (en) | Adaptive wind estimation, trajectory generation, and flight control for aerial systems using motion data | |
| Sandström et al. | Fighter pilot behavior cloning | |
| CN116627157B (en) | Carrier rocket operation control method, device and equipment | |
| Zhang et al. | Reinforcement learning control for 6 DOF flight of fixed-wing aircraft | |
| De Marco et al. | A deep reinforcement learning control approach for high-performance aircraft | |
| Kapnopoulos et al. | Quadrotor trajectory tracking based on backstepping control and radial basis function neural networks | |
| CN114815878B (en) | Hypersonic aircraft collaborative guidance method based on real-time optimization and deep learning | |
| Zhen et al. | Aircraft control method based on deep reinforcement learning | |
| CN114063636B (en) | Unmanned aerial vehicle cluster intensive formation control method and device based on interference observer | |
| CN115457809A (en) | Multi-agent reinforcement learning-based flight path planning method under opposite support scene | |
| Zhou et al. | Control of a Tail-Sitter VTOL UAV Based on Recurrent Neural Networks | |
| CN113093782A (en) | Unmanned aerial vehicle designated performance attitude control method and system | |
| Chen et al. | Deep cnn identifier for dynamic modelling of unmanned helicopter |
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: 20201027 |