CN107703953B - Attitude control method and device for unmanned aerial vehicle, unmanned aerial vehicle and storage medium - Google Patents

Attitude control method and device for unmanned aerial vehicle, unmanned aerial vehicle and storage medium Download PDF

Info

Publication number
CN107703953B
CN107703953B CN201710778431.4A CN201710778431A CN107703953B CN 107703953 B CN107703953 B CN 107703953B CN 201710778431 A CN201710778431 A CN 201710778431A CN 107703953 B CN107703953 B CN 107703953B
Authority
CN
China
Prior art keywords
unmanned aerial
aerial vehicle
flight
sliding mode
bayesian network
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
Application number
CN201710778431.4A
Other languages
Chinese (zh)
Other versions
CN107703953A (en
Inventor
周翊民
陈洪楷
吕琴
宋志斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Institute of Advanced Technology of CAS
Original Assignee
Shenzhen Institute of Advanced Technology of CAS
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Institute of Advanced Technology of CAS filed Critical Shenzhen Institute of Advanced Technology of CAS
Priority to CN201710778431.4A priority Critical patent/CN107703953B/en
Publication of CN107703953A publication Critical patent/CN107703953A/en
Application granted granted Critical
Publication of CN107703953B publication Critical patent/CN107703953B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G05D1/08—Control of attitude, i.e. control of roll, pitch, or yaw
    • G05D1/0808—Control of attitude, i.e. control of roll, pitch, or yaw specially adapted for aircraft
    • G05D1/0816—Control of attitude, i.e. control of roll, pitch, or yaw specially adapted for aircraft to ensure stability
    • G05D1/0825—Control of attitude, i.e. control of roll, pitch, or yaw specially adapted for aircraft to ensure stability using mathematical models
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
    • B60W40/04—Traffic conditions
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/08—Control of attitude, i.e. control of roll, pitch, or yaw
    • G05D1/0808—Control of attitude, i.e. control of roll, pitch, or yaw specially adapted for aircraft

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • General Physics & Mathematics (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Mathematical Physics (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Algebra (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mechanical Engineering (AREA)
  • Transportation (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

The invention is suitable for the technical field of computers, and provides an attitude control method and device of an unmanned aerial vehicle, the unmanned aerial vehicle and a storage medium, wherein the method comprises the following steps: the method comprises the steps of acquiring flight information of the unmanned aerial vehicle at the current moment through a sensor on the unmanned aerial vehicle, setting the flight information into observation data of a variable-structure discrete dynamic Bayesian network, generating flight attitude information of the unmanned aerial vehicle at the next moment through the variable-structure discrete dynamic Bayesian network, sending the flight attitude information to a ground station associated with the unmanned aerial vehicle, translating the flight attitude information into flight attitude instructions through the ground station, receiving the flight attitude instructions returned by the ground station, and controlling the flight of the unmanned aerial vehicle according to a preset time-varying sliding mode controller and the flight attitude instructions, so that the robustness and the precision of the flight control of the unmanned aerial vehicle under a complex dynamic scene (such as a disaster relief scene) are effectively improved, and the flight stability of the unmanned aerial vehicle is effectively improved.

Description

Attitude control method and device for unmanned aerial vehicle, unmanned aerial vehicle and storage medium
Technical Field
The invention belongs to the technical field of unmanned aerial vehicle attitude control, and particularly relates to an unmanned aerial vehicle attitude control method and device, an unmanned aerial vehicle and a storage medium.
Background
In the living environment of people, natural disasters and artificial disasters occur occasionally, and successful detection and rescue of workers in the field after disasters are important subjects to be faced by researchers. Compared with other disaster relief robots, the small unmanned aerial vehicle has the advantages of small influence of field environment, rapid action, high execution rate, large selectable size span and the like, so that a large number of scientific research researchers can uninterruptedly develop the application of the unmanned aerial vehicle in the aspect.
For an airborne aircraft, there are multiple levels of noise interference of unknown amplitude, unknown frequency, such as: the wind interference, the air pressure fluctuation and the temperature change are not determined locally in the space, the up-and-down flapping of the self rotor of the body is realized when the self rotor rotates, the self parameter perturbation of the body is realized, and the power moment from the external uncertain source is obtained. These disturbances make the stability of the pose of the drone a first problem if the personnel search action of the drone is available.
At present, researchers provide a method for fusing attitude data of a quad-rotor unmanned aerial vehicle based on a Kalman filter, the method reduces the calculated amount of an unmanned aerial vehicle flight control processor to a certain extent, real-time data cannot be acquired under the scene of dynamic environment change, and the anti-jamming capability of the unmanned aerial vehicle is reduced. In addition, some researchers propose to perform disturbance compensation on the initial control output quantity by expanding the observation value of position interference in the state tracker, but in the process of arranging transition, a delay problem exists in a differential signal extracted by a tracking differentiator on a controlled object, so that subsequent disturbance compensation is not facilitated. In addition, according to the Euler-Lagrange dynamics model, the flight control method of the unmanned aerial vehicle is realized by utilizing the Radial Basis Function (RBF) neural network, prior information of the Euler-Lagrange dynamics model is not needed, a good flight trajectory tracking effect is obtained, but the resource consumption of the neural network training in the method is high, and the requirement of the neural network on the accuracy of the Euler-Lagrange dynamics model is high. The method for controlling the flight of the unmanned aerial vehicle through the robust controller based on the nonlinear disturbance observer realizes the track tracking control with higher precision of the quad-rotor unmanned aerial vehicle, but the observer needs an accurate mathematical model and has low robustness, and when the unmanned aerial vehicle has uncertainty and disturbance, the performance of the observer can be reduced. The method for adaptively adjusting the switching gain in the sliding mode control by using the fuzzy neural network greatly improves the control precision and the Lupont tracking control, but the fuzzy neural network is easy to have larger deviation in the design of the subordination threshold function, has poorer adaptive capacity to the environment and finally influences the control effect.
Disclosure of Invention
The invention aims to provide an attitude control method and device of an unmanned aerial vehicle, the unmanned aerial vehicle and a storage medium, and aims to solve the problems of insufficient anti-jamming capability of the unmanned aerial vehicle, and poor robustness and accuracy of flight control of the unmanned aerial vehicle in the prior art under the condition that the unmanned aerial vehicle is interfered by uncertain wind, pressure fluctuation, temperature change and the like in a complex real environment.
In one aspect, the invention provides an attitude control method for an unmanned aerial vehicle, comprising the following steps:
acquiring flight information of the unmanned aerial vehicle at the current moment through a sensor preset on the unmanned aerial vehicle;
setting the flight information as observation data of a preset Bayesian network, and generating flight attitude information of the unmanned aerial vehicle at the next moment through the Bayesian network, wherein the Bayesian network is a variable-structure discrete dynamic Bayesian network obtained by combining training of a preset expert experience distribution model;
sending the flight attitude information to a ground station associated with the unmanned aerial vehicle, translating the flight attitude information into a flight attitude instruction through the ground station, and receiving the flight attitude instruction returned by the ground station;
and controlling the flight of the unmanned aerial vehicle according to a preset sliding mode controller with a time-varying sliding mode surface and the flight attitude instruction.
In another aspect, the present invention provides an attitude control apparatus for an unmanned aerial vehicle, the apparatus comprising:
the information acquisition unit is used for acquiring the flight information of the unmanned aerial vehicle at the current moment through a sensor preset on the unmanned aerial vehicle;
the attitude generating unit is used for setting the flight information as observation data of a preset Bayesian network, and generating the flight attitude of the unmanned aerial vehicle at the next moment through the Bayesian network, wherein the Bayesian network is a variable-structure discrete dynamic Bayesian network obtained by combining training of a preset expert experience distribution model;
the command sending unit is used for sending the flight attitude to a ground station associated with the unmanned aerial vehicle, translating the flight attitude information into a flight attitude command through the ground station, and receiving the flight attitude command returned by the ground station; and
and the flight control unit is used for controlling the flight of the unmanned aerial vehicle according to a preset sliding mode controller with a time-varying sliding mode surface and the flight attitude instruction.
In another aspect, the present invention further provides a drone, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method for controlling the attitude of the drone when executing the computer program.
In another aspect, the present invention further provides a computer-readable storage medium, which stores a computer program, and the computer program, when executed by a processor, implements the steps of the method for controlling the attitude of a drone.
The invention collects the flight information of the unmanned aerial vehicle at the current moment through a sensor on the unmanned aerial vehicle, sets the flight information as the observation data of a Bayesian network, generates the flight attitude information of the unmanned aerial vehicle at the next moment through the Bayesian network, sends the flight attitude information to a ground station associated with the unmanned aerial vehicle, translates the flight attitude information into a flight attitude command through the ground station, receives the flight attitude command returned by the ground station, controls the flight of the unmanned aerial vehicle according to a preset sliding mode controller with a time-varying sliding mode surface and the flight attitude command, so that the flight state of the unmanned aerial vehicle in a complex dynamic environment is inferred through a variable structure dynamic discrete Bayesian network combined with expert experience, the flight trajectory of the unmanned aerial vehicle is effectively tracked through the sliding mode controller with the time-varying sliding mode surface, and the robustness and precision of the flight control of the unmanned aerial vehicle are effectively improved, the stability of the unmanned aerial vehicle flying in a complex dynamic environment (such as a disaster relief environment) is stronger.
Drawings
Fig. 1 is a flowchart illustrating an implementation of an attitude control method for an unmanned aerial vehicle according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an attitude control device of an unmanned aerial vehicle according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of an attitude control device of an unmanned aerial vehicle according to a third embodiment of the present invention; and
fig. 4 is a schematic structural diagram of an unmanned aerial vehicle according to a fourth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The following detailed description of specific implementations of the present invention is provided in conjunction with specific embodiments:
the first embodiment is as follows:
fig. 1 shows an implementation flow of an attitude control method for an unmanned aerial vehicle according to a first embodiment of the present invention, and for convenience of description, only the relevant parts related to the embodiment of the present invention are shown, which are detailed as follows:
in step S101, the flight information of the unmanned aerial vehicle at the current moment is collected through a sensor preset on the unmanned aerial vehicle.
The invention is suitable for controlling the flight attitude of the unmanned aerial vehicle in a complex dynamic environment (such as a disaster relief environment). The last predetermined monocular visible light sensor (or many meshes visible light sensor) of accessible unmanned aerial vehicle, infrared light sensor, RGBD sensor, laser range finder, barometer, and positioning system etc. gather unmanned aerial vehicle current moment's flight information, flight information can include unmanned aerial vehicle's visual information, position, height, and flight gesture etc. to follow-up flight information control unmanned aerial vehicle according to gathering avoids the barrier flight.
In step S102, the flight information is set as observation data of a preset bayesian network, and the flight attitude information of the unmanned aerial vehicle at the next moment is generated through the bayesian network, where the bayesian network is a variable structure discrete dynamic bayesian network obtained by training in combination with a preset expert experience distribution model.
In the embodiment of the invention, the Bayesian network is a variable-structure discrete dynamic Bayesian network obtained by training by combining a preset expert experience distribution model. The flight information can be set as observation data of the variable-structure dynamic Bayesian network, and the flight attitude information of the unmanned aerial vehicle at the next moment is generated through a self-adaptive reasoning algorithm in the variable-structure discrete dynamic Bayesian network, so that the unmanned aerial vehicle avoids obstacles in the environment.
In the embodiment of the present invention, the network structure of the variable structure discrete dynamic bayesian network can be divided into three layers: the bottom layer is an observation node, and the evidence of the observation node is the flight information acquired by the sensor; the second layer is a hidden node which is an environment situation evaluation node of the unmanned aerial vehicle and is used for evaluating the interference type and the interference strength of the environment where the unmanned aerial vehicle is located, the relative distance between the unmanned aerial vehicle and an obstacle and the like; the top layer is a decision node, namely, the flight attitude information of the unmanned aerial vehicle at the next moment is decided, for example, before the interference in the environment occurs, the decision node comprises two types of states, namely, crossing or avoiding, and after the interference in the environment occurs, the decision node comprises three types of states, namely, advancing-avoiding, stopping-avoiding and retreating-avoiding, so that the interference in the environment is avoided in different modes according to different environment evaluations in the hidden node. And finally deducing the state of the decision node obtained by the variable-structure discrete dynamic Bayesian network, namely the flight attitude information of the unmanned aerial vehicle at the next moment.
Preferably, the construction of the expert experience distribution model and the bayesian network can be realized by the following steps:
(1) the method comprises the steps of collecting sample data of unmanned aerial vehicle flight through a sensor on the unmanned aerial vehicle, and constructing an expert experience distribution model and a Bayesian network.
(2) And optimizing parameters of the Bayesian network according to the sample data, the expert experience distribution model and the evidence of the hidden nodes in the Bayesian network to generate the trained Bayesian network.
In the embodiment of the invention, the variable-structure discrete dynamic Bayesian network reasoning is that the values of the hidden nodes and the decision nodes are calculated by using the network model parameters and the evidence of the observation nodes under the constructed network structure, and the values of the hidden nodes and the decision nodes can be determined according to the values. In a complex flight environment, the time and space of occurrence of interference have uncertainty, and the variable-structure discrete dynamic Bayesian network needs to react under a small amount of observation data (namely under sample data acquired by a sensor on the unmanned aerial vehicle in a short time), so that a phenomenon that sample data is incomplete is likely to occur. Therefore, the sampling data of the expert experience distribution model can be introduced into the parameter learning of the variable structure discrete dynamic Bayesian network by establishing the corresponding expert experience distribution model, so that the dependence of the parameter learning process on large sample data is effectively reduced to a certain extent, and the variable structure discrete dynamic Bayesian network after parameter learning obtains a more accurate reasoning result under small sample data. The expert experience distribution model can be obtained by constructing a Dirichlet (Dirichlet) distribution model or a Beta (Beta) distribution model.
In the embodiment of the invention, in the variable-structure discrete dynamic Bayesian network, the evidence of the hidden node can be obtained by forward reasoning according to the evidence (or value) of the observation node. According to the evidence of the hidden node, sample data acquired by a sensor on the unmanned aerial vehicle and samples acquired by an expert experience distribution model, parameters of the variable-structure discrete dynamic Bayesian network can be optimized to obtain the trained variable-structure discrete dynamic Bayesian network.
In step S103, the flight attitude information is sent to a ground station associated with the unmanned aerial vehicle, the flight attitude information is translated into a flight attitude command by the ground station, and the flight attitude command returned by the ground station is received.
In the embodiment of the invention, the flight attitude information obtained by variable structure discrete dynamic Bayesian network inference is sent to the ground station associated with the unmanned aerial vehicle, the ground station generates a corresponding flight attitude instruction according to the flight attitude information, and the flight attitude instruction is returned to the unmanned aerial vehicle, so that the unmanned aerial vehicle can adjust the flight attitude according to the returned flight attitude instruction.
In step S104, the flight of the unmanned aerial vehicle is controlled according to a preset sliding mode controller with a time-varying sliding mode surface and a flight attitude command.
In the embodiment of the invention, the sliding mode controller with the time-varying sliding mode surface is designed in advance, so that the problem of insufficient robustness in the conventional sliding mode control reaching stage is solved through the sliding mode controller, and the requirement on the known upper bound of uncertainty of the unmanned aerial vehicle during parameter selection of the sliding mode controller is eliminated. A sliding mode controller with a time varying sliding mode face can be designed in advance by the following steps:
(1) and constructing an initial tracking error of a preset unmanned aerial vehicle system model, and constructing a time-varying sliding mode surface according to the initial tracking error.
(2) And constructing a time-varying sliding mode control law according to the constructed time-varying sliding mode surface so as to keep the track of the unmanned aerial vehicle system model on the time-varying sliding mode surface.
In an embodiment of the present invention, the mathematical model of the drone system may be expressed as:
Figure BDA0001396380990000061
wherein xi ═ x y z]T∈R3For the gravity center position of the unmanned plane under the inertial coordinate system, V ═ Vxvyvz]T∈R3Is the linear velocity of the unmanned aerial vehicle under an inertial coordinate system, m is the mass of the unmanned aerial vehicle, and eta is phi theta psi]TThe attitude vector of the unmanned aerial vehicle under the inertial coordinate system is phi, theta and psi which are respectively a rolling angle, a pitch angle and a yaw angle, and omega is [ p qr [ ]]TThe angular velocity under the coordinate system of the unmanned aerial vehicle body is represented by p, q and R which are respectively the rolling angular velocity, the pitch angular velocity and the yaw angular velocity, J belongs to R3×3Is a rotational inertia matrix under an unmanned aerial vehicle body coordinate system, H is an attitude vector conversion matrix under the unmanned aerial vehicle body coordinate system, FLFor the total lift of four rotors of the drone, FDIs the total resistance of the four rotors of the unmanned aerial vehicle,fis the lift force moment suffered by the unmanned aerial vehicle,athe pneumatic friction torque that receives for unmanned aerial vehicle.
In the embodiment of the invention, the attitude control target of the unmanned aerial vehicle is as follows: under the condition that the disturbance upper bound of the unmanned aerial vehicle is unknown, a robust control law is designed to control the deflection angle of the fuselage to be [ 2 ]φ,θ,ψ]TRealizing attitude angle in flight attitude command
Figure BDA00013963809900000711
Tracking is carried out, namely:
Figure BDA0001396380990000071
it is true that, among other things,
Figure BDA0001396380990000072
in order to be able to track the error in the system,φ、θ、ψdeflection angles phi of roll, pitch and yaw angles, respectivelyc、θcAnd
Figure BDA0001396380990000073
respectively a roll angle, a pitch angle and a yaw angle of an attitude angle in the flight attitude command.
In the embodiment of the invention, in order to eliminate the arrival section of the traditional sliding mode and ensure the global robustness, an exponential term related to the initial tracking error of the system can be added on the basis of the traditional sliding mode surface, so that the unmanned aerial vehicle system model is positioned on the sliding mode surface from the initial moment. The constructed time-varying sliding mode surface can be expressed as:
Figure BDA0001396380990000074
wherein, Ae-atFor the exponential term related to the initial tracking error of the system, a ∈ R+Determining the approaching speed of the time-varying slip form surface to the time-invariant slip form surface, wherein A belongs to R3Is a parameter matrix related to the initial state of the unmanned aerial vehicle and is used for ensuring that S (0) ═ 03×1Can be calculated to obtain
Figure BDA0001396380990000075
And Λ is a preset parameter. Constructing a time-varying sliding mode control law (namely a robust control law) according to the constructed time-varying sliding mode surface:
Figure BDA0001396380990000076
wherein η ═ diag { η ═ eta1,η2,η3Is a switching gain matrix and satisfies ηj＞Δυjmax，ΔυjmaxIs as Δ υjMaximum value of (2) when
Figure BDA0001396380990000077
When the temperature of the water is higher than the set temperature,
Figure BDA0001396380990000078
when in use
Figure BDA0001396380990000079
At time sat(s)j(t))＝sgn(sj(t))，
Figure BDA00013963809900000710
J is 1,2,3, which is the boundary layer thickness of the time-varying slip-form face.
(3) And constructing a sliding mode controller according to the time-varying sliding mode control law and constructing a sliding mode observer, wherein the sliding mode observer is used for carrying out noise processing on the calculation of the time-varying sliding mode control law.
In the embodiment of the present invention, a sliding mode controller is constructed according to a time-varying sliding mode control law, and the sliding mode controller can be expressed as:
Figure BDA0001396380990000081
wherein z is1And (4) representing the attitude angle vector.
In the embodiment of the invention, a sliding mode observer is constructed according to a time-varying sliding mode control law, and the sliding mode observer can be expressed as follows:
Figure BDA0001396380990000082
wherein r is1、r2、r3Is an observer parameter and r1,r2,r3∈R+，
Figure BDA0001396380990000083
Are each z1And z2Is detected by the measured values of (a) and (b),
Figure BDA0001396380990000084
is an estimate of the perturbation Δ ν of the polymerisation. According to an expression formula of the time-varying sliding mode control law, when the time-varying sliding mode control law is designed, the attitude angle derivative information of the unmanned aerial vehicle is required to be used, high-frequency noise is introduced when the attitude angle is directly derived due to the influence of attitude angle measurement noise, so that the required attitude angle derivative information can be obtained by constructing a high-order sliding mode controller, and the aggregation disturbance of the time-varying sliding mode control law is estimated, so that the time-varying sliding mode control law is estimated, and the unmanned aerial vehicle is controlled by the high-order sliding mode controllerThe precision of unmanned aerial vehicle attitude control is improved effectively.
In the embodiment of the invention, after the flight information of the unmanned aerial vehicle at the current moment is acquired, the flight information is processed through the Bayesian network to generate the flight attitude information of the unmanned aerial vehicle at the next moment, the flight attitude information is translated into the flight attitude command by the ground station associated with the unmanned aerial vehicle, and the flight of the unmanned aerial vehicle is controlled according to the preset sliding mode controller with the time-varying sliding mode surface and the flight attitude command, so that the flight state of the unmanned aerial vehicle in a complex dynamic environment is inferred through the variable structure dynamic discrete Bayesian network combined with expert experience, the flight track of the unmanned aerial vehicle is effectively tracked through the sliding mode control model with the time-varying sliding mode surface, the robustness and the precision of the flight control of the unmanned aerial vehicle are effectively improved, and the flight stability of the unmanned aerial vehicle in the complex dynamic environment is stronger.
Example two:
fig. 2 shows a structure of an attitude control device of an unmanned aerial vehicle according to a second embodiment of the present invention, and for convenience of description, only parts related to the second embodiment of the present invention are shown, where the structure includes:
and the information acquisition unit 21 is used for acquiring the flight information of the unmanned aerial vehicle at the current moment through a preset sensor on the unmanned aerial vehicle.
In the embodiment of the invention, the flight information of the unmanned aerial vehicle at the current moment can be acquired through a monocular visible light sensor (or a multi-ocular visible light sensor), an infrared light sensor, an RGBD sensor, a laser range finder, a barometer, a positioning system and the like preset on the unmanned aerial vehicle, and the flight information can comprise the visual information, the position, the height, the flight attitude and the like of the unmanned aerial vehicle, so that the unmanned aerial vehicle can be controlled to fly away from the obstacle according to the acquired flight information.
And the attitude generating unit 22 is configured to set the flight information as observation data of a preset bayesian network, and generate the flight attitude information of the unmanned aerial vehicle at the next moment through the bayesian network, where the bayesian network is a variable structure discrete dynamic bayesian network obtained by combining training of a preset expert experience distribution model.
In the embodiment of the invention, the Bayesian network is a variable-structure discrete dynamic Bayesian network obtained by combining training of a preset expert experience distribution model. The flight information can be set as observation data of the variable-structure discrete dynamic Bayesian network, and the flight attitude information of the unmanned aerial vehicle at the next moment is generated through a self-adaptive reasoning algorithm in the variable-structure discrete dynamic Bayesian network, so that the unmanned aerial vehicle avoids obstacles in the environment.
In the embodiment of the present invention, the network structure of the variable structure discrete dynamic bayesian network can be divided into three layers: the bottom layer is an observation node, and the evidence of the observation node is the flight information acquired by the sensor; the second layer is a hidden node which is an environment situation evaluation node of the unmanned aerial vehicle and is used for evaluating the interference type and the interference strength of the environment where the unmanned aerial vehicle is located, the relative distance between the unmanned aerial vehicle and an obstacle and the like; the top layer is a decision node, namely, the flight attitude information of the unmanned aerial vehicle at the next moment is decided, for example, before the interference in the environment occurs, the decision node comprises two types of states, namely, crossing or avoiding, and after the interference in the environment occurs, the decision node comprises three types of states, namely, advancing-avoiding, stopping-avoiding and retreating-avoiding, so that the interference in the environment is avoided in different modes according to different environment evaluations in the hidden node. And finally deducing the state of the decision node obtained by the variable-structure discrete dynamic Bayesian network, namely the flight attitude information of the unmanned aerial vehicle at the next moment.
And the instruction sending unit 23 is configured to send the flight attitude information to a ground station associated with the unmanned aerial vehicle, translate the flight attitude information into a flight attitude instruction through the ground station, and receive the flight attitude instruction returned by the ground station.
In the embodiment of the invention, the flight attitude information obtained by variable structure discrete dynamic Bayesian network inference is sent to the ground station associated with the unmanned aerial vehicle, the ground station generates a corresponding flight attitude instruction according to the flight attitude information, and the flight attitude instruction is returned to the unmanned aerial vehicle, so that the unmanned aerial vehicle can adjust the flight attitude according to the returned flight attitude instruction.
And the flight control unit 24 is used for controlling the flight of the unmanned aerial vehicle by a preset sliding mode controller with a time-varying sliding mode surface and a flight attitude instruction.
In the embodiment of the invention, the sliding mode controller with the time-varying sliding mode surface is designed in advance, so that the problem of insufficient robustness in the conventional sliding mode control reaching stage is solved through the sliding mode controller, and the requirement on the known upper bound of uncertainty of the unmanned aerial vehicle during parameter selection of the sliding mode controller is eliminated. And the sliding mode controller with the time-varying sliding mode surface is used for processing the flight attitude instruction to realize the flight control of the unmanned aerial vehicle.
In the embodiment of the invention, after the flight information of the unmanned aerial vehicle at the current moment is acquired, the flight information is processed through the Bayesian network to generate the flight attitude information of the unmanned aerial vehicle at the next moment, the flight attitude information is translated into the flight attitude command by the ground station associated with the unmanned aerial vehicle, and the flight of the unmanned aerial vehicle is controlled according to the preset sliding mode controller with the time-varying sliding mode surface and the flight attitude command, so that the flight state of the unmanned aerial vehicle in a complex dynamic environment is inferred through the variable structure dynamic discrete Bayesian network combined with expert experience, the flight track of the unmanned aerial vehicle is effectively tracked through the sliding mode control model with the time-varying sliding mode surface, the robustness and the precision of the flight control of the unmanned aerial vehicle are effectively improved, and the flight stability of the unmanned aerial vehicle in the complex dynamic environment is stronger.
Example three:
fig. 3 shows a structure of an attitude control device of an unmanned aerial vehicle according to a third embodiment of the present invention, and for convenience of description, only the portions related to the third embodiment of the present invention are shown, where the structure includes:
and the network model building unit 31 is used for acquiring sample data of the flight of the unmanned aerial vehicle through a sensor on the unmanned aerial vehicle and building an expert experience distribution model and a Bayesian network.
And the network training unit 32 is configured to optimize parameters of the bayesian network according to the sample data, the expert experience distribution model, and the evidence of the hidden nodes in the bayesian network, and generate a trained bayesian network.
In the embodiment of the invention, the variable-structure discrete dynamic Bayesian network reasoning is that the values of the hidden nodes and the decision nodes are calculated by using the network model parameters and the evidence of the observation nodes under the constructed network structure, and the values of the hidden nodes and the decision nodes can be determined according to the values. In a complex flight environment, the time and space of occurrence of interference have uncertainty, and the variable-structure discrete dynamic Bayesian network needs to react under a small amount of observation data (namely under sample data acquired by a sensor on the unmanned aerial vehicle in a short time), so that a phenomenon that sample data is incomplete is likely to occur. Therefore, the sampling data of the expert experience distribution model can be introduced into the parameter learning of the variable structure discrete dynamic Bayesian network by establishing the corresponding expert experience distribution model, so that the dependence of the parameter learning process on large sample data is effectively reduced to a certain extent, and the variable structure discrete dynamic Bayesian network after parameter learning obtains a more accurate reasoning result under small sample data. The expert experience distribution model can be obtained by constructing a Dirichlet (Dirichlet) distribution model or a Beta (Beta) distribution model.
In the embodiment of the invention, in the variable-structure discrete dynamic Bayesian network, the evidence of the hidden node can be obtained by forward reasoning according to the evidence (or value) of the observation node. According to the evidence of the hidden node, sample data acquired by a sensor on the unmanned aerial vehicle and samples acquired by an expert experience distribution model, parameters of the variable-structure discrete dynamic Bayesian network can be optimized to obtain the trained variable-structure discrete dynamic Bayesian network.
And the sliding mode surface construction unit 33 is used for constructing an initial tracking error of a preset unmanned aerial vehicle system model, and constructing a time-varying sliding mode surface according to the initial tracking error.
And the control law constructing unit 34 is used for constructing a time-varying sliding mode control law according to the constructed time-varying sliding mode surface so as to keep the track of the unmanned aerial vehicle system model on the time-varying sliding mode surface.
In an embodiment of the present invention, the model of the drone system may be represented as:
Figure BDA0001396380990000111
wherein xi ═ x y z]T∈R3For the gravity center position of the unmanned plane under the inertial coordinate system, V ═ Vxvyvz]T∈R3Is the linear velocity of the unmanned aerial vehicle under the inertial coordinate system, m is the mass of the unmanned aerial vehicle, eta ═ phi theta psi]TThe attitude vector of the unmanned aerial vehicle under the inertial coordinate system is phi, theta and psi which are respectively a rolling angle, a pitching angle and a yaw angle, and omega is [ pqr [ ]]TThe angular velocity under the coordinate system of the unmanned aerial vehicle body is represented by p, q and R which are respectively the rolling angular velocity, the pitch angular velocity and the yaw angular velocity, J belongs to R3×3Is a rotational inertia matrix under an unmanned aerial vehicle body coordinate system, H is an attitude vector conversion matrix under the unmanned aerial vehicle body coordinate system, FLFor the total lift of four rotors of the drone, FDIs the total resistance of the four rotors of the unmanned aerial vehicle,fis the lift force moment suffered by the unmanned aerial vehicle,athe pneumatic friction torque that receives for unmanned aerial vehicle.
In the embodiment of the invention, the attitude control target of the unmanned aerial vehicle is as follows: under the condition that the disturbance upper bound of the unmanned aerial vehicle is unknown, a robust control law is designed to control the deflection angle of the fuselage to be [ 2 ]φ,θ,ψ]TRealizing attitude angle in flight attitude command
Figure BDA0001396380990000121
Tracking is carried out, namely:
Figure BDA0001396380990000122
it is true that, among other things,
Figure BDA0001396380990000123
in order to be able to track the error in the system,φ、θ、ψdeflection angles phi of roll, pitch and yaw angles, respectivelyc、θcAnd
Figure BDA0001396380990000124
roll angle, pitch angle and yaw angle of attitude angle in flight attitude command respectively。
In the embodiment of the invention, in order to eliminate the arrival section of the traditional sliding mode and ensure the global robustness, an exponential term related to the initial tracking error of the system can be added on the basis of the traditional sliding mode surface, so that the unmanned aerial vehicle system model is positioned on the sliding mode surface from the initial moment. The constructed time-varying sliding mode surface can be expressed as:
Figure BDA0001396380990000125
wherein, Ae-atFor the exponential term related to the initial tracking error of the system, a ∈ R+Determining the approaching speed of the time-varying slip form surface to the time-invariant slip form surface, wherein A belongs to R3Is a parameter matrix related to the initial state of the unmanned aerial vehicle and is used for ensuring that S (0) ═ 03×1Can be calculated to obtain
Figure BDA0001396380990000126
And Λ is a preset parameter. Constructing a time-varying sliding mode control law (namely a robust control law) according to the constructed time-varying sliding mode surface:
Figure BDA0001396380990000127
wherein η ═ diag { η ═ eta1,η2,η3Is a switching gain matrix and satisfies ηj＞Δυjmax，ΔυjmaxIs as Δ υjMaximum value of (2) when
Figure BDA0001396380990000128
When the temperature of the water is higher than the set temperature,
Figure BDA0001396380990000129
when in use
Figure BDA00013963809900001210
At time sat(s)j(t))＝sgn(sj(t))，
Figure BDA00013963809900001211
J is 1,2,3, which is the boundary layer thickness of the time-varying slip-form face.
The controller constructing unit 35 is configured to construct a sliding mode controller according to the time-varying sliding mode control law, and construct a sliding mode observer, where the sliding mode observer is used to perform noise processing on the calculation of the time-varying sliding mode control law.
In the embodiment of the present invention, a sliding mode controller is constructed according to a time-varying sliding mode control law, and the sliding mode controller can be expressed as:
Figure BDA00013963809900001212
wherein z is1And (4) representing the attitude angle vector.
In the embodiment of the invention, a sliding mode observer is constructed according to a time-varying sliding mode control law, and the sliding mode observer can be expressed as follows:
Figure BDA0001396380990000131
wherein r is1、r2、r3Is an observer parameter and r1,r2,r3∈R+，
Figure BDA0001396380990000132
Are each z1And z2Is detected by the measured values of (a) and (b),
Figure BDA0001396380990000133
is an estimate of the perturbation Δ ν of the polymerisation. According to an expression formula of the time-varying sliding mode control law, when the time-varying sliding mode control law is designed, attitude angle derivative information of the unmanned aerial vehicle needs to be used, high-frequency noise can be introduced by directly deriving the attitude angle due to the influence of attitude angle measurement noise, so that the required attitude angle derivative information can be obtained by constructing a high-order sliding mode controller, the aggregation disturbance of the time-varying sliding mode control law is estimated, and the flying attitude control precision of the unmanned aerial vehicle is effectively improved.
And the information acquisition unit 36 is used for acquiring the flight information of the unmanned aerial vehicle at the current moment through a preset sensor on the unmanned aerial vehicle.
In the embodiment of the invention, the flight information of the unmanned aerial vehicle at the current moment can be acquired through a monocular visible light sensor (or a multi-ocular visible light sensor), an infrared light sensor, an RGBD sensor, a laser range finder, a barometer, a positioning system and the like preset on the unmanned aerial vehicle, and the flight information can comprise the visual information, the position, the height, the flight attitude and the like of the unmanned aerial vehicle, so that the unmanned aerial vehicle can be controlled to fly away from the obstacle according to the acquired flight information.
And the attitude generating unit 37 is configured to set the flight information as observation data of a preset bayesian network, and generate the flight attitude information of the unmanned aerial vehicle at the next moment through the bayesian network, where the bayesian network is a variable structure discrete dynamic bayesian network obtained by combining training of a preset expert experience distribution model.
In the embodiment of the invention, the Bayesian network is a variable-structure discrete dynamic Bayesian network obtained by combining training of a preset expert experience distribution model. The flight information can be set as observation data of the variable-structure dynamic Bayesian network, and the flight attitude information of the unmanned aerial vehicle at the next moment is generated through a self-adaptive reasoning algorithm in the variable-structure discrete dynamic Bayesian network, so that the unmanned aerial vehicle avoids obstacles in the environment.
In the embodiment of the present invention, the network structure of the variable structure discrete dynamic bayesian network can be divided into three layers: the bottom layer is an observation node, and the evidence of the observation node is the flight information acquired by the sensor; the second layer is a hidden node which is an environment situation evaluation node of the unmanned aerial vehicle and is used for evaluating the interference type and the interference strength of the environment where the unmanned aerial vehicle is located, the relative distance between the unmanned aerial vehicle and an obstacle and the like; the top layer is a decision node, namely, the flight attitude information of the unmanned aerial vehicle at the next moment is decided, for example, before the interference in the environment occurs, the decision node comprises two types of states, namely, crossing or avoiding, and after the interference in the environment occurs, the decision node comprises three types of states, namely, advancing-avoiding, stopping-avoiding and retreating-avoiding, so that the interference in the environment is avoided in different modes according to different environment evaluations in the hidden node. And finally deducing the state of the decision node obtained by the variable-structure discrete dynamic Bayesian network, namely the flight attitude information of the unmanned aerial vehicle at the next moment.
And the instruction sending unit 38 is configured to send the flight attitude information to a ground station associated with the unmanned aerial vehicle, translate the flight attitude information into a flight attitude instruction through the ground station, and receive the flight attitude instruction returned by the ground station.
In the embodiment of the invention, the flight attitude information obtained by variable structure discrete dynamic Bayesian network inference is sent to the ground station associated with the unmanned aerial vehicle, the ground station generates a corresponding flight attitude instruction according to the flight attitude information, and the flight attitude instruction is returned to the unmanned aerial vehicle, so that the unmanned aerial vehicle can adjust the flight attitude according to the returned flight attitude instruction.
And the flight control unit 39 is used for controlling the flight of the unmanned aerial vehicle according to a preset sliding mode controller with a time-varying sliding mode surface and a flight attitude instruction.
In the embodiment of the invention, the sliding mode controller with the time-varying sliding mode surface is designed in advance, so that the problem of insufficient robustness in the conventional sliding mode control reaching stage is solved through the sliding mode controller, and the requirement on the known upper bound of uncertainty of the unmanned aerial vehicle during parameter selection of the sliding mode controller is eliminated. And the sliding mode controller with the time-varying sliding mode surface is used for processing the flight attitude instruction to realize the flight control of the unmanned aerial vehicle.
In the embodiment of the invention, after the flight information of the unmanned aerial vehicle at the current moment is acquired, the flight information is processed through the Bayesian network to generate the flight attitude information of the unmanned aerial vehicle at the next moment, the flight attitude information is translated into the flight attitude command by the ground station associated with the unmanned aerial vehicle, and the flight of the unmanned aerial vehicle is controlled according to the preset sliding mode controller with the time-varying sliding mode surface and the flight attitude command, so that the flight state of the unmanned aerial vehicle in a complex dynamic environment is inferred through the variable structure dynamic discrete Bayesian network combined with expert experience, the flight track of the unmanned aerial vehicle is effectively tracked through the sliding mode control model with the time-varying sliding mode surface, the robustness and the precision of the flight control of the unmanned aerial vehicle are effectively improved, and the flight stability of the unmanned aerial vehicle in the complex dynamic environment is stronger.
In the embodiment of the present invention, each unit of the attitude control device of the unmanned aerial vehicle may be implemented by a corresponding hardware or software unit, and each unit may be an independent software or hardware unit, or may be integrated into a software or hardware unit, which is not limited herein.
Example four:
fig. 4 shows a structure of the unmanned aerial vehicle according to the fourth embodiment of the present invention, and for convenience of explanation, only the portions related to the embodiment of the present invention are shown.
The drone 4 of an embodiment of the present invention includes a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. The processor 40, when executing the computer program 42, implements the steps of the above-described method embodiments, such as the steps S101 to S104 shown in fig. 1. Alternatively, the processor 40, when executing the computer program 42, implements the functions of the units in the above-described device embodiments, such as the functions of the units 21 to 24 shown in fig. 2.
In the embodiment of the invention, after the flight information of the unmanned aerial vehicle at the current moment is acquired, the flight information is processed through the Bayesian network to generate the flight attitude information of the unmanned aerial vehicle at the next moment, the flight attitude information is translated into the flight attitude command by the ground station associated with the unmanned aerial vehicle, and the flight of the unmanned aerial vehicle is controlled according to the preset sliding mode controller with the time-varying sliding mode surface and the flight attitude command, so that the flight state of the unmanned aerial vehicle in a complex dynamic environment is inferred through the variable structure dynamic discrete Bayesian network combined with expert experience, the flight track of the unmanned aerial vehicle is effectively tracked through the sliding mode control model with the time-varying sliding mode surface, the robustness and the precision of the flight control of the unmanned aerial vehicle are effectively improved, and the flight stability of the unmanned aerial vehicle in the complex dynamic environment is stronger.
Example five:
in an embodiment of the present invention, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the steps in the above-described method embodiments, e.g., steps S101 to S104 shown in fig. 1. Alternatively, the computer program may be adapted to perform the functions of the units of the above-described device embodiments, such as the functions of the units 21 to 24 shown in fig. 2, when executed by the processor.
In the embodiment of the invention, after the flight information of the unmanned aerial vehicle at the current moment is acquired, the flight information is processed through the Bayesian network to generate the flight attitude information of the unmanned aerial vehicle at the next moment, the flight attitude information is translated into the flight attitude command by the ground station associated with the unmanned aerial vehicle, and the flight of the unmanned aerial vehicle is controlled according to the preset sliding mode controller with the time-varying sliding mode surface and the flight attitude command, so that the flight state of the unmanned aerial vehicle in a complex dynamic environment is inferred through the variable structure dynamic discrete Bayesian network combined with expert experience, the flight track of the unmanned aerial vehicle is effectively tracked through the sliding mode control model with the time-varying sliding mode surface, the robustness and the precision of the flight control of the unmanned aerial vehicle are effectively improved, and the flight stability of the unmanned aerial vehicle in the complex dynamic environment is stronger.
The computer readable storage medium of the embodiments of the present invention may include any entity or device capable of carrying computer program code, a recording medium, such as a ROM/RAM, a magnetic disk, an optical disk, a flash memory, or the like.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.

Claims (6)

1. An attitude control method of an unmanned aerial vehicle, characterized by comprising the steps of:
acquiring flight information of the unmanned aerial vehicle at the current moment through a sensor preset on the unmanned aerial vehicle;
setting the flight information as observation data of a preset Bayesian network, and generating flight attitude information of the unmanned aerial vehicle at the next moment through the Bayesian network, wherein the Bayesian network is a variable-structure discrete dynamic Bayesian network obtained by combining training of a preset expert experience distribution model; the Bayesian network comprises observation nodes, hidden nodes and decision nodes, wherein the observation nodes are flight information acquired by the sensors, the hidden nodes are environment situation evaluation nodes of the unmanned aerial vehicle, and the decision nodes comprise flight attitudes of the unmanned aerial vehicle before and after interference;
sending the flight attitude information to a ground station associated with the unmanned aerial vehicle, translating the flight attitude information into a flight attitude instruction through the ground station, and receiving the flight attitude instruction returned by the ground station;
controlling the flight of the unmanned aerial vehicle according to a preset sliding mode controller with a time-varying sliding mode surface and the flight attitude instruction;
before the step of acquiring the flight information of the unmanned aerial vehicle at the current moment through a preset sensor on the unmanned aerial vehicle, the method further comprises the following steps:
constructing an initial tracking error of a preset unmanned aerial vehicle system model, and constructing the time-varying sliding mode surface according to the initial tracking error;
constructing a time-varying sliding mode control law according to the constructed time-varying sliding mode surface so as to keep the track of the unmanned aerial vehicle system model on the time-varying sliding mode surface;
and constructing the sliding mode controller according to the time-varying sliding mode control law and constructing a sliding mode observer, wherein the sliding mode observer is used for carrying out noise processing on the calculation of the time-varying sliding mode control law.
2. The method of claim 1, wherein the step of collecting the flight information of the drone at the current time is preceded by a step of collecting the flight information of the drone through sensors preset on the drone, the method further comprising:
acquiring sample data of the unmanned aerial vehicle flying through a sensor on the unmanned aerial vehicle, and constructing the expert experience distribution model and the Bayesian network;
and optimizing parameters of the Bayesian network according to the sample data, the expert experience distribution model and the evidence of hidden nodes in the Bayesian network to generate the trained Bayesian network.
3. An attitude control device for unmanned aerial vehicles, the device comprising:
the information acquisition unit is used for acquiring the flight information of the unmanned aerial vehicle at the current moment through a sensor preset on the unmanned aerial vehicle;
the attitude generating unit is used for setting the flight information as observation data of a preset Bayesian network, and generating flight attitude information of the unmanned aerial vehicle at the next moment through the Bayesian network, wherein the Bayesian network is a variable-structure discrete dynamic Bayesian network obtained by combining training of a preset expert experience distribution model; the Bayesian network comprises observation nodes, hidden nodes and decision nodes, wherein the observation nodes are flight information acquired by the sensors, the hidden nodes are environment situation evaluation nodes of the unmanned aerial vehicle, and the decision nodes comprise flight attitudes of the unmanned aerial vehicle before and after interference;
the command sending unit is used for sending the flight attitude information to a ground station associated with the unmanned aerial vehicle, translating the flight attitude information into a flight attitude command through the ground station, and receiving the flight attitude command returned by the ground station; and
the flight control unit is used for controlling the flight of the unmanned aerial vehicle according to a preset sliding mode controller with a time-varying sliding mode surface and the flight attitude instruction;
the sliding mode surface construction unit is used for constructing an initial tracking error of a preset unmanned aerial vehicle system model and constructing the time-varying sliding mode surface according to the initial tracking error;
the control law construction unit is used for constructing a time-varying sliding mode control law according to the constructed time-varying sliding mode surface so as to keep the track of the unmanned aerial vehicle system model on the time-varying sliding mode surface; and
and the controller construction unit is used for constructing the sliding mode controller according to the time-varying sliding mode control law and constructing a sliding mode observer, and the sliding mode observer is used for carrying out noise processing on the calculation of the time-varying sliding mode control law.
4. The apparatus of claim 3, wherein the apparatus further comprises:
the network model building unit is used for acquiring sample data of the unmanned aerial vehicle flying through a sensor on the unmanned aerial vehicle and building the expert experience distribution model and the Bayesian network; and
and the network training unit is used for optimizing parameters of the Bayesian network according to the sample data, the expert experience distribution model and the evidence of hidden nodes in the Bayesian network to generate the trained Bayesian network.
5. A drone comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1 to 2 when executing the computer program.
6. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 2.
CN201710778431.4A 2017-09-01 2017-09-01 Attitude control method and device for unmanned aerial vehicle, unmanned aerial vehicle and storage medium Active CN107703953B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710778431.4A CN107703953B (en) 2017-09-01 2017-09-01 Attitude control method and device for unmanned aerial vehicle, unmanned aerial vehicle and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710778431.4A CN107703953B (en) 2017-09-01 2017-09-01 Attitude control method and device for unmanned aerial vehicle, unmanned aerial vehicle and storage medium

Publications (2)

Publication Number Publication Date
CN107703953A CN107703953A (en) 2018-02-16
CN107703953B true CN107703953B (en) 2020-10-23

Family

ID=61171378

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710778431.4A Active CN107703953B (en) 2017-09-01 2017-09-01 Attitude control method and device for unmanned aerial vehicle, unmanned aerial vehicle and storage medium

Country Status (1)

Country Link
CN (1) CN107703953B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108427289B (en) * 2018-04-27 2021-06-29 哈尔滨工业大学 Hypersonic aircraft tracking control method based on nonlinear function
CN110333737A (en) * 2019-07-05 2019-10-15 湖北理工学院 A kind of high unmanned aerial vehicle control system of spraying efficiency for pesticide spraying and method
CN113641181B (en) * 2020-04-27 2023-05-26 华中科技大学 Aircraft gain self-adaptive attitude control method and system based on online performance evaluation
CN112904866B (en) * 2021-01-28 2023-04-21 西安建筑科技大学 Warehouse-in charging control method and system for inspection robot and outdoor inspection robot

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2010008639A1 (en) * 2008-04-09 2010-01-21 Christopher William Weller Intelligent jungle canopy surveillance appartus and method
WO2015147715A1 (en) * 2014-03-28 2015-10-01 Telefonaktiebolaget L M Ericsson (Publ) Method and device for controlling an autonomous device

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7983450B2 (en) * 2009-03-16 2011-07-19 The Boeing Company Method, apparatus and computer program product for recognizing a gesture
CN102426806B (en) * 2011-11-07 2014-01-29 同济大学 Regional rail network UAV cruise method based on dynamic cell division
CN103472850B (en) * 2013-09-29 2015-11-18 合肥工业大学 A kind of multiple no-manned plane collaboratively searching method based on Gaussian distribution prediction
US9715234B2 (en) * 2015-11-30 2017-07-25 Metal Industries Research & Development Centre Multiple rotors aircraft and control method
CN106155054A (en) * 2016-07-05 2016-11-23 中国科学院深圳先进技术研究院 Wheel carries out control system and the method for composite mobile robot
CN106802658B (en) * 2017-03-21 2019-09-20 厦门大学 Method for rapidly positioning in a kind of full-automatic high precision room

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2010008639A1 (en) * 2008-04-09 2010-01-21 Christopher William Weller Intelligent jungle canopy surveillance appartus and method
WO2015147715A1 (en) * 2014-03-28 2015-10-01 Telefonaktiebolaget L M Ericsson (Publ) Method and device for controlling an autonomous device

Also Published As

Publication number Publication date
CN107703953A (en) 2018-02-16

Similar Documents

Publication Publication Date Title
Wang et al. Deep-reinforcement-learning-based autonomous UAV navigation with sparse rewards
CN107703953B (en) Attitude control method and device for unmanned aerial vehicle, unmanned aerial vehicle and storage medium
Li et al. Adaptive RBFNNs/integral sliding mode control for a quadrotor aircraft
Hatamleh et al. Unmanned aerial vehicles parameter estimation using artificial neural networks and iterative bi-section shooting method
Ambroziak et al. Two stage switching control for autonomous formation flight of unmanned aerial vehicles
CN112462797B (en) Visual servo control method and system using grey prediction model
Islam et al. Adaptive sliding mode control of unmanned four rotor flying vehicle
Sarabakha et al. Y6 tricopter autonomous evacuation in an indoor environment using Q-learning algorithm
CN115494879A (en) Rotor unmanned aerial vehicle obstacle avoidance method, device and equipment based on reinforcement learning SAC
CN112859913A (en) Multi-quad-rotor unmanned aerial vehicle attitude consistency optimal control method considering output constraint
Ourari et al. Nearest-neighbor-based collision avoidance for quadrotors via reinforcement learning
Bobtsov et al. Hybrid parallel neuro-controller for multirotor unmanned aerial vehicle
CN109375642B (en) Energy-saving control method for unmanned aerial vehicle
Bodi et al. Reinforcement learning based UAV formation control in GPS-denied environment
WO2022126396A1 (en) State information determination method and apparatus, and platform and computer-readable storage medium
Watanabe et al. Optimal 3-D guidance from a 2-D vision sensor
Duoxiu et al. Proximal policy optimization for multi-rotor uav autonomous guidance, tracking and obstacle avoidance
CN110162084B (en) Formation control method of flying missile cluster system based on consistency theory
Valencia et al. Trajectory tracking control for multiple quadrotors based on a neurobiological-inspired system
CN113885549B (en) Four-rotor gesture track control method based on dimension clipping PPO algorithm
CN116088311A (en) Unmanned helicopter second-order uncertain sliding mode control method based on adaptive neural network extended state observer
Richter et al. Using double deep q-learning to learn attitude control of fixed-wing aircraft
Ramirez et al. Stability analysis of a vision-based UAV controller: An application to autonomous road following missions
Verberne Development of Robust Control Laws for Disturbance Rejection in Rotorcraft UAVs
Jurado et al. Continuous-time decentralized neural control of a quadrotor UAV

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant